SlideShare uma empresa Scribd logo
1 de 35
Baixar para ler offline
Unbiased Gradient Estimation for Marginal Log-likelihood
Shohei Taniguchi, Matsuo Lab
എ‫ܠ‬
• ਂ૚ੜ੒Ϟσϧͷֶश͸ɼपลର਺໬౓ ͷ࠷େԽͰఆࣜԽ͞ΕΔ


જࡏม਺Ϟσϧʢe.g., VAE)ɿ


ΤωϧΪʔϕʔεϞσϧɿ


• ଟ͘ͷ৔߹Ͱɼपลର਺໬౓͸ղੳతʹ‫͍ͳ͖Ͱࢉܭ‬
log pθ (x)
log pθ (x) = log
∫
pθ (x, z) dz
log pθ (x) = − Eθ (x) − log
∫
exp (−Eθ (x)) dx
2
എ‫ܠ‬
ྫ̍ɿVAE


ର਺पล໬౓ͷม෼ԼքͰۙࣅ


log pθ (x) = log
∫
pθ (x, z) dz
≥
𝔼
q(z) [
log
pθ (x, z)
q (z) ]
= ℒ (θ, q)
3
എ‫ܠ‬
ྫ̎ɿEBM


ର਺पล໬౓ͷޯ഑ΛMCMCͰۙࣅ




͸MCMCΛ εςοϓճͨ͠෼෍Ͱɼ Ͱ౳߸੒ཱ
∇log pθ (x+) = − ∇Eθ (x+) +
𝔼
x−∼pθ(x) [∇Eθ (x−)]
≈ − ∇Eθ (x+) +
𝔼
xT∼q(xT) [∇Eθ (xT)]
q (xT) T T → ∞
4
എ‫ܠ‬
• ม෼Լք΍༗‫ݶ‬εςοϓͷMCMCʹΑΔޯ഑ͷۙࣅʹ͸ɼόΠΞε͕͋Δ


όΠΞεɿਪఆྔͷ‫ظ‬଴஋ͱਅ஋ͱͷͣΕ
ɹɹɹɹɹόΠΞε͕0ͷਪఆྔΛෆภਪఆྔͱ͍͏


• Ͱ͖Ε͹ɼର਺पล໬౓ͷޯ഑ͷෆภਪఆྔΛ࢖ֶͬͯश͍ͨ͠


• ର਺पล໬౓Λෆภਪఆ͢Δख๏ͷྫʢա‫ڈ‬ͷྠಡʣ
https://www.slideshare.net/DeepLearningJP2016/dlsumo-unbiased-estimation-
of-log-marginal-probability-for-latent-variable-models-250013351
5
Outline
पลର਺໬౓ͷෆภਪఆ๏
1. पลର਺໬౓ࣗମΛਪఆ͢Δํ๏


• On Multilevel Monte Carlo Unbiased Gradient Estimation for Deep Latent
Variable Models (AISTATS 2021)


• Efficient Debiased Evidence Estimation by Multilevel Monte Carlo Sampling (UAI
2021)


2. पลର਺໬౓ͷޯ഑Λਪఆ͢Δํ๏


• Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent
Variable Models (ICLR 2020)
6
Outline
पลର਺໬౓ͷෆภਪఆ๏
1. पลର਺໬౓ࣗମΛਪఆ͢Δํ๏


• On Multilevel Monte Carlo Unbiased Gradient Estimation for Deep Latent
Variable Models (AISTATS 2021)


• Efficient Debiased Evidence Estimation by Multilevel Monte Carlo Sampling (UAI
2021)


2. पลର਺໬౓ͷޯ഑Λਪఆ͢Δํ๏


• Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent
Variable Models (ICLR 2020)
7
IWAE
Importance Weighted Autoencoder
ͰVAEͱҰகɼ Ͱ౳߸੒ཱ
log pθ (x) = log
𝔼
z(1),…,z(k)∼q(z)
[
1
k
k
∑
i=1
pθ (x, z(i)
)
q (z(i)
) ]
≥
𝔼
z(1),…,z(k)∼q(z)
[
log
1
k
k
∑
i=1
pθ (x, z(i)
)
q (z(i)
) ]
=
𝔼
z(1),…,z(k)∼q(z) [ℒk (θ, q)]
k = 1 k → ∞
पลର਺໬౓ͷ‫਺ڃ‬ද‫ه‬


ͱ͓͘ͱɺ‫਺ڃ‬ ͷ‫ظ‬଴஋͸ର਺पล໬౓ͱҰக͢Δ


Δk =
{
ℒ1 (θ, q) (k = 1)
ℒk (θ, q) − ℒk−1 (θ, q) (k ≥ 2)
∞
∑
k=1
Δk
𝔼
[
∞
∑
k=1
Δk
]
=
𝔼
[ℒ∞ (θ, q)] = log pθ (x)
Russian Roulette Estimator
ҎԼͷΑ͏ͳ Λߟ͑Δ




1. ֬཰ Ͱද͕ग़ΔίΠϯΛৼΔ


2. ද͕ग़ͨΒ Ҏ߱Λ‫͠ࢉܭ‬ɺ Ͱׂͬͨ΋ͷΛ ʹ଍͢
ཪ͕ग़ͨΒ ͚ͩΛ‫͢ࢉܭ‬Δ
̂
y
̂
y = Δ1 +
∑
∞
k=2
Δk
μ
⋅ b, b ∼ Bernoulli (μ)
μ
k = 2 μ Δ1
Δ1
Russian Roulette Estimator
͸ ͷෆภਪఆྔͰ͋Δ͜ͱ͕Θ͔Δ






̂
y
∞
∑
k=1
Δk
̂
y = Δ1 +
∑
∞
k=2
Δk
μ
⋅ b, b ∼ Bernoulli (b; μ)
𝔼
[ ̂
y] = Δ1 +
∑
∞
k=2
Δk
μ
⋅
𝔼
[b] =
∞
∑
k=1
Δk
Russian Roulette Estimator
ಉ͜͡ͱΛ Ҏ߱΋‫܁‬Γฦ͢ͱɺҎԼͷ ΋ ͷෆภਪఆྔʹͳΔ




͸࠷ॳʹཪ͕ग़Δ·ͰʹίΠϯΛৼͬͨճ਺ʢ‫ز‬Կ෼෍ʹै͏ʣ


͜ͷ Λ࢖͑͹ɺର਺पล໬౓ͷෆภਪఆྔ͕ಘΒΕΔ
k = 2 ̂
y
∞
∑
k=1
Δk
̂
y =
K
∑
k=1
Δk
μk−1
, K ∼ Geometric (K; 1 − μ)
K
̂
y
Single Sample Estimator
ಉ༷ʹͯ͠ɼҎԼͷ ΋ ͷෆภਪఆྔʹͳΔ


̂
y
∞
∑
k=1
Δk
̂
y =
ΔK
p (K)
=
ΔK
μK−1
(1 − μ)
𝔼
[ ̂
y] =
∞
∑
K=1
p (K) ⋅
ΔK
p (K)
=
∞
∑
k=1
Δk
SUMO
Stochastically Unbiased Marginalization Objective
log pθ (x) =
𝔼
K∼p(K)
[
K
∑
k=1
Δk
μk−1 ]
= ℒ1 (θ, qϕ) +
𝔼
K∼p(K)
K
∑
k=2
ℒk (θ, qϕ) − ℒk−1 (θ, qϕ)
μk−1
VAEͱಉ͡
ิਖ਼߲
SUMOͷ՝୊
• ਪఆྔͷ෼ࢄ͕େ͖͘ͳΓ΍͍͢


• ࠷ѱͷ৔߹ɼ෼ࢄ͕ແ‫ݶ‬େʹൃࢄ͢Δ


• ෼ࢄ͸ ͷબͼํͰ੍‫͖Ͱޚ‬Δ͕ɼ෼ࢄΛԼ͛Α͏ͱ͢Δͱɼ
͕େ͖͘ͳΓɼ‫͕ྔࢉܭ‬େ͖͘ͳΔ


• ෼ࢄ͕༗‫ྔࢉܭ͔ͭݶ‬ͷ‫ظ‬଴஋΋༗‫͋Ͱݶ‬Δ͜ͱ͕ཧ૝
p (K)
K
15
पลର਺໬౓ͷ‫਺ڃ‬ද‫ه‬ʢ࠶ʣ


ͱ͓͘ͱɺ‫਺ڃ‬ ͷ‫ظ‬଴஋͸ର਺पล໬౓ͱҰக͢Δ


Δk =
{
ℒ1 (θ, q) (k = 1)
ℒk (θ, q) − ℒk−1 (θ, q) (k ≥ 2)
∞
∑
k=1
Δk
𝔼
[
∞
∑
k=1
Δk
]
=
𝔼
[ℒ∞ (θ, q)] = log pθ (x)
ͷઃ‫ํܭ‬๏͸ଞʹ΋ߟ͑ΒΕΔ
Δk
पลର਺໬౓ͷ‫਺ڃ‬ද‫ه‬ʢվʣ


͜ͷ৔߹΋ɼ‫਺ڃ‬ ͷ‫ظ‬଴஋͸ର਺पล໬౓ͱҰக͢Δ


͜ΕΛ࢖ͬͯߏ੒ͨ͠ਪఆྔ͸ɼ෼ࢄ༗‫ྔࢉܭ͔ͭݶ‬༗‫ݶ‬Λ࣮‫͖Ͱݱ‬Δ
Δk =
ℒ1 (θ, q) (k = 1)
ℒ2k (θ, q)−
1
2 (ℒ(1)
2k−1 (θ, q) + ℒ(2)
2k−1 (θ, q)) (k ≥ 2)
∞
∑
k=1
Δk
࣮‫ݧ‬
ը૾ੜ੒
ఏҊ๏͸IWAE΍SUMOΑΓ΋ੑೳ͕վળ͢Δ
Outline
पลର਺໬౓ͷෆภਪఆ๏
1. पลର਺໬౓ࣗମΛਪఆ͢Δํ๏


• On Multilevel Monte Carlo Unbiased Gradient Estimation for Deep Latent
Variable Models (AISTATS 2021)


• Efficient Debiased Evidence Estimation by Multilevel Monte Carlo Sampling (UAI
2021)


2. पลର਺໬౓ͷޯ഑Λਪఆ͢Δํ๏


• Unbiased Contrastive Divergence Algorithm for Training Energy-Based Latent
Variable Models (ICLR 2020)
19
EBMͷֶश
ର਺पล໬౓ͷޯ഑ΛMCMCͰۙࣅ




͸MCMCΛ εςοϓճͨ͠෼෍Ͱɼ Ͱ౳߸੒ཱ


͕༗‫ͱͩݶ‬ɼޯ഑ͷਪఆʹόΠΞε͕ͷΔ
∇log pθ (x+) = − ∇Eθ (x+) +
𝔼
x−∼pθ(x) [∇Eθ (x−)]
≈ − ∇Eθ (x+) +
𝔼
xT∼q(xT) [∇Eθ (xT)]
q (xT) T T → ∞
T
20
ޯ഑ͷ‫਺ڃ‬ల։


Ͱ͋Δ͜ͱΛ༻͍Δͱɼ‫਺ڃ‬ͷ‫ʹܗ‬ม‫͖Ͱܗ‬Δ
𝔼
x−∼pθ(x) [∇Eθ (x−)]
=
𝔼
x∞∼q(x∞) [∇Eθ (x∞)]
=
𝔼
xk∼q(xk) [∇Eθ (xk)] +
∞
∑
t=k+1
𝔼
xt+1∼q(xt+1) [∇Eθ (xt+1)] −
𝔼
xt∼q(xt) [∇Eθ (xt)]
pθ (x) = q (x∞)
21
ޯ഑ͷ‫਺ڃ‬ల։


ͨͩ͠ɼ ͸ ͱಉ͡पล෼෍ʹै͏
𝔼
x−∼pθ(x) [∇Eθ (x−)]
=
𝔼
xk∼q(xk) [∇Eθ (xk)] +
∞
∑
t=k+1
𝔼
xt+1∼q(xt+1) [∇Eθ (xt+1)] −
𝔼
xt∼q(xt) [∇Eθ (xt)]
=
𝔼
xk∼q(xk) [∇Eθ (xk)] +
∞
∑
t=k+1
𝔼
xt+1∼q(xt+1) [∇Eθ (xt+1)]−
𝔼
yt∼q(yt) [∇Eθ (yt)]
yt xt
22
ޯ഑ͷ‫਺ڃ‬ల։


ͨͩ͠ɼ ͸ ͱಉ͡पล෼෍ʹै͏
𝔼
x−∼pθ(x) [∇Eθ (x−)]
=
𝔼
xk∼q(xk) [∇Eθ (xk)] +
∞
∑
t=k+1
𝔼
xt+1∼q(xt+1) [∇Eθ (xt+1)]−
𝔼
yt∼q(yt) [∇Eθ (yt)]
=
𝔼
[
∇Eθ (xk) +
∞
∑
t=k+1
(∇Eθ (xt+1) − ∇Eθ (yt))]
yt xt
23
ޯ഑ͷ‫਺ڃ‬ల։


ͨͩ͠ɼ ͸ ͱಉ͡पล෼෍ʹै͍ɼ Ͱ Ͱ͋Δͱ͢Δ
𝔼
x−∼pθ(x) [∇Eθ (x−)]
=
𝔼
[
∇Eθ (xk) +
∞
∑
t=k+1
(∇Eθ (xt+1) − ∇Eθ (yt))
]
=
𝔼
[
∇Eθ (xk) +
τ−1
∑
t=k+1
(∇Eθ (xt+1) − ∇Eθ (yt))
]
yt xt t ≥ τ xt+1 = yt
24
ޯ഑ͷ‫਺ڃ‬ల։


ແ‫਺ڃݶ‬Λ༗‫ݶ‬࿨ʹॻ͖‫͑׵‬ΒΕͨʂ


͔͠͠ɼ Ͱ Λຬͨ͢ ͸ͲͷΑ͏ʹ࡞Δʁ
𝔼
x−∼pθ(x) [∇Eθ (x−)]
=
𝔼
[
∇Eθ (xk) +
τ−1
∑
t=k+1
(∇Eθ (xt+1) − ∇Eθ (yt))]
t ≥ τ xt+1 = yt yt
25
ΧοϓϦϯά
• ૬ؔͷ͋Δ2ͭͷMCMCΛճͯ͠
1εςοϓͣΕͨαϯϓϧಉ͕࢜
Ұக͢Δ·Ͱճ͢
• MCMCΛಠཱʹճͯ͠͠·͏ͱ
αϯϓϧಉ͕࢜Ұக͢Δ͜ͱ͕΄ͱΜͲ‫͜ى‬Βͳ͍ͷͰ
͏·͘૬ؔͤ͞Δ͜ͱ͕ٕज़తͳ؊
26
ΧοϓϦϯά
• ͱ ΛͦΕͧΕ ʹै͏֬཰ม਺ͱ͢Δ


• ͨͩ͠ɼ྆ऀ͸ಠཱͰ͋Δඞཁ͸ͳ͍
• ͜ͷͱ͖ɼ ͱ ͕Ұக͢Δ֬཰ ʹ͍ͭͯɼҎԼͷෆ౳͕ࣜ੒ཱ


ξ η p (ξ), q (η)
ξ η P (ξ = η)
P(ξ = η) ≤ 1 − ∥p − q∥TV =
∫
min{p(x), q(x)}dx
27
∫
min{p(x), q(x)}dx
Maximal Coupling


• ҎԼͷखॱͰ ͱ ΛαϯϓϦϯά͢Δͱɼ͜ͷ্քΛୡ੒Ͱ͖Δ
P(ξ = η) ≤ 1 − ∥p − q∥TV =
∫
min{p(x), q(x)}dx
ξ η
28
https://commons.wikimedia.org/wiki/File:Total_variation_distance.svg
Maximal Coupling
खॱ
1. ෼෍ ͔Β ΛαϯϓϦϯά


2. ֬཰ Ͱ ͱ͢Δ


• ਤͷ੺͍෦෼͔Β Λαϯϓϧ


3. ֬཰ Ͱ ͔Βαϯϓϧ͢Δ


• ͷ࢒Γͷ෦෼͔Β Λαϯϓϧ
p ξ
α = min (q (ξ)/p (ξ), 1) η = ξ
η
1 − α q̃ (η) ∝ min (q (η) − p (η), 0)
q η
29
https://commons.wikimedia.org/wiki/File:Total_variation_distance.svg
Maximal Coupling
ྫɿͲͪΒ΋ඪ४ਖ਼‫ن‬෼෍ͷ৔߹


1. ͔Βαϯϓϧ ΛಘΔ


2. ͱͯ͠ɼ ͔Βͷ
αϯϓϧͱ͢Δ
• ͜ͷͱ͖ɼ ͱ ͸ͱ΋ʹඪ४ਖ਼‫ن‬෼෍ʹै͍ɼ֬཰1Ͱ
p ξ
η = ξ q
ξ η ξ = η
30
https://colcarroll.github.io/couplings/static/maximal_couplings.html
Maximal Coupling
ͦͷଞͷྫ
31
https://colcarroll.github.io/couplings/static/maximal_couplings.html
ΧοϓϦϯά
• MCMCͷ֤εςοϓΛmaximal couplingͰαϯϓϦϯά͢Δ͜ͱͰ
ߴ͍֬཰Ͱ2ͭͷαϯϓϧΛҰகͤ͞Δ͜ͱ͕Ͱ͖Δ


• ΧοϓϦϯάΛ࢖ͬͨMCMCͷෆภԽͷॳग़͸[Jacob, et al., 2017]
https://arxiv.org/abs/1708.03625


• ͜ͷ࿦จ͸ɼ͜ΕΛEBMʢಛʹRBMʣͷ
ֶशʹ༻͍ͨ΋ͷ
32
࣮‫ݧ‬
τΠσʔλ
33
ී௨ͷMCMCͰ͸్த͔Βੑೳ͕ྼԽ͢Δ͕ఏҊ๏͸ͦΕ͕‫͜ى‬Βͳ͍
ΧοϓϦϯάʹ͔͔Δεςοϓ਺͸ଟͯ͘10εςοϓఔ౓
࣮‫ݧ‬
ը૾ੜ੒ʢFashion MNISTʣ
34
ը૾ੜ੒Ͱ΋ಉ༷ͷ܏޲
·ͱΊ
• पลର਺໬౓͓Αͼͦͷޯ഑Λෆภਪఆ͢ΔͨΊͷςΫχοΫΛ঺հ


1. ϩγΞϯϧʔϨοτਪఆΛ༗‫ݶ‬෼ࢄɾ༗‫ํ͏ߦͰྔࢉܭݶ‬๏


2. ΧοϓϦϯάΛ࢖ͬͯMCMCΛෆภʹ͢Δํ๏


• ͲͪΒ΋ςΫχΧϧʹ໘ന͘ɼ৭ʑԠ༻͕ޮ͖ͦ͏


• ࣮‫͕ݧ‬খ‫ن‬໛ͳͷͰɼେ͖͍ϞσϧͰ΋࢖͑Δͷ͔͕‫ͳʹؾ‬Δ
35

Mais conteúdo relacionado

Mais procurados

Deeplearning輪読会
Deeplearning輪読会Deeplearning輪読会
Deeplearning輪読会正志 坪坂
 
[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative ModelsDeep Learning JP
 
(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot Learning(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot LearningMasahiro Suzuki
 
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence ModelingDeep Learning JP
 
強化学習と逆強化学習を組み合わせた模倣学習
強化学習と逆強化学習を組み合わせた模倣学習強化学習と逆強化学習を組み合わせた模倣学習
強化学習と逆強化学習を組み合わせた模倣学習Eiji Uchibe
 
深層生成モデルと世界モデル
深層生成モデルと世界モデル深層生成モデルと世界モデル
深層生成モデルと世界モデルMasahiro Suzuki
 
PyMCがあれば,ベイズ推定でもう泣いたりなんかしない
PyMCがあれば,ベイズ推定でもう泣いたりなんかしないPyMCがあれば,ベイズ推定でもう泣いたりなんかしない
PyMCがあれば,ベイズ推定でもう泣いたりなんかしないToshihiro Kamishima
 
2014 3 13(テンソル分解の基礎)
2014 3 13(テンソル分解の基礎)2014 3 13(テンソル分解の基礎)
2014 3 13(テンソル分解の基礎)Tatsuya Yokota
 
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...Deep Learning JP
 
深層生成モデルを用いたマルチモーダル学習
深層生成モデルを用いたマルチモーダル学習深層生成モデルを用いたマルチモーダル学習
深層生成モデルを用いたマルチモーダル学習Masahiro Suzuki
 
[DL輪読会]逆強化学習とGANs
[DL輪読会]逆強化学習とGANs[DL輪読会]逆強化学習とGANs
[DL輪読会]逆強化学習とGANsDeep Learning JP
 
Control as Inference (強化学習とベイズ統計)
Control as Inference (強化学習とベイズ統計)Control as Inference (強化学習とベイズ統計)
Control as Inference (強化学習とベイズ統計)Shohei Taniguchi
 
猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoder猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoderSho Tatsuno
 
[DL輪読会]Temporal DifferenceVariationalAuto-Encoder
[DL輪読会]Temporal DifferenceVariationalAuto-Encoder[DL輪読会]Temporal DifferenceVariationalAuto-Encoder
[DL輪読会]Temporal DifferenceVariationalAuto-EncoderDeep Learning JP
 
最適輸送の計算アルゴリズムの研究動向
最適輸送の計算アルゴリズムの研究動向最適輸送の計算アルゴリズムの研究動向
最適輸送の計算アルゴリズムの研究動向ohken
 
変分推論法(変分ベイズ法)(PRML第10章)
変分推論法(変分ベイズ法)(PRML第10章)変分推論法(変分ベイズ法)(PRML第10章)
変分推論法(変分ベイズ法)(PRML第10章)Takao Yamanaka
 
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
[DL輪読会]Dream to Control: Learning Behaviors by Latent ImaginationDeep Learning JP
 
「世界モデル」と関連研究について
「世界モデル」と関連研究について「世界モデル」と関連研究について
「世界モデル」と関連研究についてMasahiro Suzuki
 
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion ModelsDeep Learning JP
 
数学で解き明かす深層学習の原理
数学で解き明かす深層学習の原理数学で解き明かす深層学習の原理
数学で解き明かす深層学習の原理Taiji Suzuki
 

Mais procurados (20)

Deeplearning輪読会
Deeplearning輪読会Deeplearning輪読会
Deeplearning輪読会
 
[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models[DL輪読会]Flow-based Deep Generative Models
[DL輪読会]Flow-based Deep Generative Models
 
(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot Learning(DL輪読)Matching Networks for One Shot Learning
(DL輪読)Matching Networks for One Shot Learning
 
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
[DL輪読会]Decision Transformer: Reinforcement Learning via Sequence Modeling
 
強化学習と逆強化学習を組み合わせた模倣学習
強化学習と逆強化学習を組み合わせた模倣学習強化学習と逆強化学習を組み合わせた模倣学習
強化学習と逆強化学習を組み合わせた模倣学習
 
深層生成モデルと世界モデル
深層生成モデルと世界モデル深層生成モデルと世界モデル
深層生成モデルと世界モデル
 
PyMCがあれば,ベイズ推定でもう泣いたりなんかしない
PyMCがあれば,ベイズ推定でもう泣いたりなんかしないPyMCがあれば,ベイズ推定でもう泣いたりなんかしない
PyMCがあれば,ベイズ推定でもう泣いたりなんかしない
 
2014 3 13(テンソル分解の基礎)
2014 3 13(テンソル分解の基礎)2014 3 13(テンソル分解の基礎)
2014 3 13(テンソル分解の基礎)
 
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
【DL輪読会】SUMO: Unbiased Estimation of Log Marginal Probability for Latent Varia...
 
深層生成モデルを用いたマルチモーダル学習
深層生成モデルを用いたマルチモーダル学習深層生成モデルを用いたマルチモーダル学習
深層生成モデルを用いたマルチモーダル学習
 
[DL輪読会]逆強化学習とGANs
[DL輪読会]逆強化学習とGANs[DL輪読会]逆強化学習とGANs
[DL輪読会]逆強化学習とGANs
 
Control as Inference (強化学習とベイズ統計)
Control as Inference (強化学習とベイズ統計)Control as Inference (強化学習とベイズ統計)
Control as Inference (強化学習とベイズ統計)
 
猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoder猫でも分かるVariational AutoEncoder
猫でも分かるVariational AutoEncoder
 
[DL輪読会]Temporal DifferenceVariationalAuto-Encoder
[DL輪読会]Temporal DifferenceVariationalAuto-Encoder[DL輪読会]Temporal DifferenceVariationalAuto-Encoder
[DL輪読会]Temporal DifferenceVariationalAuto-Encoder
 
最適輸送の計算アルゴリズムの研究動向
最適輸送の計算アルゴリズムの研究動向最適輸送の計算アルゴリズムの研究動向
最適輸送の計算アルゴリズムの研究動向
 
変分推論法(変分ベイズ法)(PRML第10章)
変分推論法(変分ベイズ法)(PRML第10章)変分推論法(変分ベイズ法)(PRML第10章)
変分推論法(変分ベイズ法)(PRML第10章)
 
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
[DL輪読会]Dream to Control: Learning Behaviors by Latent Imagination
 
「世界モデル」と関連研究について
「世界モデル」と関連研究について「世界モデル」と関連研究について
「世界モデル」と関連研究について
 
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
【DL輪読会】High-Resolution Image Synthesis with Latent Diffusion Models
 
数学で解き明かす深層学習の原理
数学で解き明かす深層学習の原理数学で解き明かす深層学習の原理
数学で解き明かす深層学習の原理
 

Semelhante a 【DL輪読会】Unbiased Gradient Estimation for Marginal Log-likelihood

Phase diagram at finite T & Mu in strong coupling limit of lattice QCD
Phase diagram at finite T & Mu in strong coupling limit of lattice QCDPhase diagram at finite T & Mu in strong coupling limit of lattice QCD
Phase diagram at finite T & Mu in strong coupling limit of lattice QCDBenjamin Jaedon Choi
 
Scattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysisScattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysisVjekoslavKovac1
 
An Efficient Boundary Integral Method for Stiff Fluid Interface Problems
An Efficient Boundary Integral Method for Stiff Fluid Interface ProblemsAn Efficient Boundary Integral Method for Stiff Fluid Interface Problems
An Efficient Boundary Integral Method for Stiff Fluid Interface ProblemsAlex (Oleksiy) Varfolomiyev
 
Modeling the Dynamics of SGD by Stochastic Differential Equation
Modeling the Dynamics of SGD by Stochastic Differential EquationModeling the Dynamics of SGD by Stochastic Differential Equation
Modeling the Dynamics of SGD by Stochastic Differential EquationMark Chang
 
Hiroyuki Sato
Hiroyuki SatoHiroyuki Sato
Hiroyuki SatoSuurist
 
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...Tomoya Murata
 
ゲーム理論BASIC 演習6 -仁を求める-
ゲーム理論BASIC 演習6 -仁を求める-ゲーム理論BASIC 演習6 -仁を求める-
ゲーム理論BASIC 演習6 -仁を求める-ssusere0a682
 
統計的学習の基礎 4章 前半
統計的学習の基礎 4章 前半統計的学習の基礎 4章 前半
統計的学習の基礎 4章 前半Ken'ichi Matsui
 
Signals and Systems Formula Sheet
Signals and Systems Formula SheetSignals and Systems Formula Sheet
Signals and Systems Formula SheetHaris Hassan
 
Pre-calculus 1, 2 and Calculus I (exam notes)
Pre-calculus 1, 2 and Calculus I (exam notes)Pre-calculus 1, 2 and Calculus I (exam notes)
Pre-calculus 1, 2 and Calculus I (exam notes)William Faber
 
ゲーム理論BASIC 演習52 -完全ベイジアン均衡-
ゲーム理論BASIC 演習52 -完全ベイジアン均衡-ゲーム理論BASIC 演習52 -完全ベイジアン均衡-
ゲーム理論BASIC 演習52 -完全ベイジアン均衡-ssusere0a682
 
graphs of quadratic function grade 9.pptx
graphs of quadratic function grade 9.pptxgraphs of quadratic function grade 9.pptx
graphs of quadratic function grade 9.pptxMeryAnnMAlday
 
cps170_bayes_nets.ppt
cps170_bayes_nets.pptcps170_bayes_nets.ppt
cps170_bayes_nets.pptFaizAbaas
 
Functions of severable variables
Functions of severable variablesFunctions of severable variables
Functions of severable variablesSanthanam Krishnan
 
Using blurred images to assess damage in bridge structures?
Using blurred images to assess damage in bridge structures?Using blurred images to assess damage in bridge structures?
Using blurred images to assess damage in bridge structures? Alessandro Palmeri
 

Semelhante a 【DL輪読会】Unbiased Gradient Estimation for Marginal Log-likelihood (20)

Phase diagram at finite T & Mu in strong coupling limit of lattice QCD
Phase diagram at finite T & Mu in strong coupling limit of lattice QCDPhase diagram at finite T & Mu in strong coupling limit of lattice QCD
Phase diagram at finite T & Mu in strong coupling limit of lattice QCD
 
Scattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysisScattering theory analogues of several classical estimates in Fourier analysis
Scattering theory analogues of several classical estimates in Fourier analysis
 
An Efficient Boundary Integral Method for Stiff Fluid Interface Problems
An Efficient Boundary Integral Method for Stiff Fluid Interface ProblemsAn Efficient Boundary Integral Method for Stiff Fluid Interface Problems
An Efficient Boundary Integral Method for Stiff Fluid Interface Problems
 
Modeling the Dynamics of SGD by Stochastic Differential Equation
Modeling the Dynamics of SGD by Stochastic Differential EquationModeling the Dynamics of SGD by Stochastic Differential Equation
Modeling the Dynamics of SGD by Stochastic Differential Equation
 
Hiroyuki Sato
Hiroyuki SatoHiroyuki Sato
Hiroyuki Sato
 
PRODUCT RULES
PRODUCT RULESPRODUCT RULES
PRODUCT RULES
 
2018 MUMS Fall Course - Mathematical surrogate and reduced-order models - Ral...
2018 MUMS Fall Course - Mathematical surrogate and reduced-order models - Ral...2018 MUMS Fall Course - Mathematical surrogate and reduced-order models - Ral...
2018 MUMS Fall Course - Mathematical surrogate and reduced-order models - Ral...
 
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
Doubly Accelerated Stochastic Variance Reduced Gradient Methods for Regulariz...
 
ゲーム理論BASIC 演習6 -仁を求める-
ゲーム理論BASIC 演習6 -仁を求める-ゲーム理論BASIC 演習6 -仁を求める-
ゲーム理論BASIC 演習6 -仁を求める-
 
統計的学習の基礎 4章 前半
統計的学習の基礎 4章 前半統計的学習の基礎 4章 前半
統計的学習の基礎 4章 前半
 
Signals and Systems Formula Sheet
Signals and Systems Formula SheetSignals and Systems Formula Sheet
Signals and Systems Formula Sheet
 
Pre-calculus 1, 2 and Calculus I (exam notes)
Pre-calculus 1, 2 and Calculus I (exam notes)Pre-calculus 1, 2 and Calculus I (exam notes)
Pre-calculus 1, 2 and Calculus I (exam notes)
 
Krishna
KrishnaKrishna
Krishna
 
ゲーム理論BASIC 演習52 -完全ベイジアン均衡-
ゲーム理論BASIC 演習52 -完全ベイジアン均衡-ゲーム理論BASIC 演習52 -完全ベイジアン均衡-
ゲーム理論BASIC 演習52 -完全ベイジアン均衡-
 
graphs of quadratic function grade 9.pptx
graphs of quadratic function grade 9.pptxgraphs of quadratic function grade 9.pptx
graphs of quadratic function grade 9.pptx
 
2018 MUMS Fall Course - Statistical Representation of Model Input (EDITED) - ...
2018 MUMS Fall Course - Statistical Representation of Model Input (EDITED) - ...2018 MUMS Fall Course - Statistical Representation of Model Input (EDITED) - ...
2018 MUMS Fall Course - Statistical Representation of Model Input (EDITED) - ...
 
cps170_bayes_nets.ppt
cps170_bayes_nets.pptcps170_bayes_nets.ppt
cps170_bayes_nets.ppt
 
Functions of severable variables
Functions of severable variablesFunctions of severable variables
Functions of severable variables
 
legendre.pptx
legendre.pptxlegendre.pptx
legendre.pptx
 
Using blurred images to assess damage in bridge structures?
Using blurred images to assess damage in bridge structures?Using blurred images to assess damage in bridge structures?
Using blurred images to assess damage in bridge structures?
 

Mais de Deep Learning JP

【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving PlannersDeep Learning JP
 
【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについてDeep Learning JP
 
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...Deep Learning JP
 
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-ResolutionDeep Learning JP
 
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxivDeep Learning JP
 
【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLMDeep Learning JP
 
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo... 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...Deep Learning JP
 
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place RecognitionDeep Learning JP
 
【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?Deep Learning JP
 
【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究についてDeep Learning JP
 
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )Deep Learning JP
 
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...Deep Learning JP
 
【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"
【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"
【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"Deep Learning JP
 
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "Deep Learning JP
 
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat ModelsDeep Learning JP
 
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"Deep Learning JP
 
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...Deep Learning JP
 
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...Deep Learning JP
 
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...Deep Learning JP
 
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...Deep Learning JP
 

Mais de Deep Learning JP (20)

【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
【DL輪読会】AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners
 
【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて【DL輪読会】事前学習用データセットについて
【DL輪読会】事前学習用データセットについて
 
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
【DL輪読会】 "Learning to render novel views from wide-baseline stereo pairs." CVP...
 
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
【DL輪読会】Zero-Shot Dual-Lens Super-Resolution
 
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
【DL輪読会】BloombergGPT: A Large Language Model for Finance arxiv
 
【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM【DL輪読会】マルチモーダル LLM
【DL輪読会】マルチモーダル LLM
 
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo... 【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
【 DL輪読会】ToolLLM: Facilitating Large Language Models to Master 16000+ Real-wo...
 
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
【DL輪読会】AnyLoc: Towards Universal Visual Place Recognition
 
【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?【DL輪読会】Can Neural Network Memorization Be Localized?
【DL輪読会】Can Neural Network Memorization Be Localized?
 
【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について【DL輪読会】Hopfield network 関連研究について
【DL輪読会】Hopfield network 関連研究について
 
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
【DL輪読会】SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )
 
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
【DL輪読会】RLCD: Reinforcement Learning from Contrast Distillation for Language M...
 
【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"
【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"
【DL輪読会】"Secrets of RLHF in Large Language Models Part I: PPO"
 
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "【DL輪読会】"Language Instructed Reinforcement Learning  for Human-AI Coordination "
【DL輪読会】"Language Instructed Reinforcement Learning for Human-AI Coordination "
 
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
【DL輪読会】Llama 2: Open Foundation and Fine-Tuned Chat Models
 
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
【DL輪読会】"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware"
 
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
【DL輪読会】Parameter is Not All You Need:Starting from Non-Parametric Networks fo...
 
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
【DL輪読会】Drag Your GAN: Interactive Point-based Manipulation on the Generative ...
 
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
【DL輪読会】Self-Supervised Learning from Images with a Joint-Embedding Predictive...
 
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
【DL輪読会】Towards Understanding Ensemble, Knowledge Distillation and Self-Distil...
 

Último

ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesrafiqahmad00786416
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfOrbitshub
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024The Digital Insurer
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodJuan lago vázquez
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistandanishmna97
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...Zilliz
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxRustici Software
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024The Digital Insurer
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Victor Rentea
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...DianaGray10
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobeapidays
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MIND CTI
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businesspanagenda
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FMESafe Software
 
Cyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfCyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfOverkill Security
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Zilliz
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingEdi Saputra
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAndrey Devyatkin
 

Último (20)

ICT role in 21st century education and its challenges
ICT role in 21st century education and its challengesICT role in 21st century education and its challenges
ICT role in 21st century education and its challenges
 
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdfRising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
Rising Above_ Dubai Floods and the Fortitude of Dubai International Airport.pdf
 
Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024Manulife - Insurer Transformation Award 2024
Manulife - Insurer Transformation Award 2024
 
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin WoodPolkadot JAM Slides - Token2049 - By Dr. Gavin Wood
Polkadot JAM Slides - Token2049 - By Dr. Gavin Wood
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
CNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In PakistanCNIC Information System with Pakdata Cf In Pakistan
CNIC Information System with Pakdata Cf In Pakistan
 
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ..."I see eyes in my soup": How Delivery Hero implemented the safety system for ...
"I see eyes in my soup": How Delivery Hero implemented the safety system for ...
 
Corporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptxCorporate and higher education May webinar.pptx
Corporate and higher education May webinar.pptx
 
AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024AXA XL - Insurer Innovation Award Americas 2024
AXA XL - Insurer Innovation Award Americas 2024
 
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
Modular Monolith - a Practical Alternative to Microservices @ Devoxx UK 2024
 
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
Connector Corner: Accelerate revenue generation using UiPath API-centric busi...
 
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, AdobeApidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
Apidays New York 2024 - Scaling API-first by Ian Reasor and Radu Cotescu, Adobe
 
MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024MINDCTI Revenue Release Quarter One 2024
MINDCTI Revenue Release Quarter One 2024
 
Why Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire businessWhy Teams call analytics are critical to your entire business
Why Teams call analytics are critical to your entire business
 
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers:  A Deep Dive into Serverless Spatial Data and FMECloud Frontiers:  A Deep Dive into Serverless Spatial Data and FME
Cloud Frontiers: A Deep Dive into Serverless Spatial Data and FME
 
Cyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdfCyberprint. Dark Pink Apt Group [EN].pdf
Cyberprint. Dark Pink Apt Group [EN].pdf
 
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
Emergent Methods: Multi-lingual narrative tracking in the news - real-time ex...
 
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost SavingRepurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
Repurposing LNG terminals for Hydrogen Ammonia: Feasibility and Cost Saving
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
AWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of TerraformAWS Community Day CPH - Three problems of Terraform
AWS Community Day CPH - Three problems of Terraform
 

【DL輪読会】Unbiased Gradient Estimation for Marginal Log-likelihood