Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
論文紹介: Sample Reuse via Importance Sampling in I...
Search
Masahiro Nomura
April 09, 2020
Research
0
280
論文紹介: Sample Reuse via Importance Sampling in Information Geometric Optimization / sample_reuse_igo
Masahiro Nomura
April 09, 2020
Tweet
Share
More Decks by Masahiro Nomura
See All by Masahiro Nomura
ランダム欠損データに依存しない推薦システムのバイアス除去 / towards-resolving-propensity-contradiction-in-offline-recommender-learning
nmasahiro
0
290
転移学習によるハイパーパラメータ最適化の高速化 / warm_starting_cma
nmasahiro
0
2.2k
論文紹介: IRのためのパラメータチューニング / ir-tuning
nmasahiro
0
520
機械学習における ハイパーパラメータ最適化の理論と実践 / hpo_theory_practice
nmasahiro
30
41k
論文紹介 : Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
nmasahiro
1
750
広告とAI(とハイパーパラメータ最適化) / Ad with AI
nmasahiro
1
2.1k
Other Decks in Research
See All in Research
HU Berlin: Industrial-Strength Natural Language Processing with spaCy and Prodigy
inesmontani
PRO
0
120
J-RAGBench: 日本語RAGにおける Generator評価ベンチマークの構築
koki_itai
0
1.1k
高畑鬼界ヶ島と重文・称名寺本薬師如来像の来歴を追って/kikaigashima
kochizufan
0
110
説明可能な機械学習と数理最適化
kelicht
2
800
[Devfest Incheon 2025] 모두를 위한 친절한 언어모델(LLM) 학습 가이드
beomi
2
1.4k
教師あり学習と強化学習で作る 最強の数学特化LLM
analokmaus
2
820
An Open and Reproducible Deep Research Agent for Long-Form Question Answering
ikuyamada
0
170
Remote sensing × Multi-modal meta survey
satai
4
670
Nullspace MPC
mizuhoaoki
1
570
長期・短期メモリを活用したエージェントの個別最適化
isidaitc
0
380
競合や要望に流されない─B2B SaaSでミニマム要件を決めるリアルな取り組み / Don't be swayed by competitors or requests - A real effort to determine minimum requirements for B2B SaaS
kaminashi
0
450
20251023_くまもと21の会例会_「車1割削減、渋滞半減、公共交通2倍」をめざして.pdf
trafficbrain
0
150
Featured
See All Featured
Code Reviewing Like a Champion
maltzj
527
40k
Bash Introduction
62gerente
615
210k
Money Talks: Using Revenue to Get Sh*t Done
nikkihalliwell
0
130
The Limits of Empathy - UXLibs8
cassininazir
1
200
Being A Developer After 40
akosma
91
590k
Darren the Foodie - Storyboard
khoart
PRO
0
2.1k
Ten Tips & Tricks for a 🌱 transition
stuffmc
0
46
Agile Leadership in an Agile Organization
kimpetersen
PRO
0
65
Tell your own story through comics
letsgokoyo
0
770
ラッコキーワード サービス紹介資料
rakko
0
1.9M
職位にかかわらず全員がリーダーシップを発揮するチーム作り / Building a team where everyone can demonstrate leadership regardless of position
madoxten
54
48k
Evolving SEO for Evolving Search Engines
ryanjones
0
91
Transcript
. Sample Reuse via Importance Sampling in Information Geometric Optimization
^ILW1NL Y 18 : I ) ) * ( WP LW WPK ^ 1
• . S RL ?L XL [P 8S UWY L
S RP N P 8 MUWS YPU 7LUSLYWP = YPSP YPU • . OP P OP OPW DU OLP 1 PSUYU P = OP U U =O W • . WCP[ ) (- 75 = (+ L]YL K • . w 87= ʼ • . 28: 1 5 h • . 1 5 z~ 2
• 87= • 87= • • 3
87= • i i i • . s p f
s • w ~n • 1 5 5 . ]ac nʼ s • 28: 71 . ]ac nʼ • w z~ 1 5 ? e A K YL 4
87= • 87= (. • M I M 5
87= • zrzf5EM ] F sm • y • z~
s n • z~ 5EB ] F 6
87= • zrzf5EM ] F sm • y • z~
s n • z~ 5EB ] F 7
87= • zrzf5EM ] F sm • y • z~
s n • z~ 5EB ] F 8
87= • zrzf5EM ] F sm • y • z~
s n • z~ 5EB ] F 9
87= • now f5EB ] F w ʼ • ~
• 87= ). • N I S • . • : KP[s • i rv w 10
87= • • d ]ac r • • 5EB ]
F zfc 11
87= • • d ]ac r • • 5EB ]
F zfc • d ~ sm 12
87= • 87= d n~n • PYLW YPU x ~~z
~ f t~n n • ~ ~ 13
8S UWY L S RP N • ( G /
( f r s • zʼn . ] b G N ] ∫ " # %& # '# • i . G r d • n 8 . • A IP XLKr|f G zʼ s n 14
• 28: . ]ac nʼ87= • • 1 5 .
]ac nʼ87= • z n z k 15
. 28: 16 • = L ] . ( ʼ
s ~(s • :L KP N= LX . r (s zʼ s ~(s
. 1 5 17 • 5RRP XUPK ?UXL IWU .
• 1 RL^ ? XYWPNP . • ? XYWPNP s1 RL^ s n
. 1 5 18
• 87= ʼ i i • 28: 1 5 •
8S UWY L S RP N • 28: 1 5 z~ • ? XYWPNP zr ʼsf • • 19