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
290
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
310
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
2.3k
論文紹介: IRのためのパラメータチューニング / ir-tuning
nmasahiro
0
530
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
42k
論文紹介 : Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
nmasahiro
1
770
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
衛星×エッジAI勉強会 衛星上におけるAI処理制約とそ取組について
satai
4
290
学習型データ構造:機械学習を内包する新しいデータ構造の設計と解析
matsui_528
6
3.7k
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
380
【NICOGRAPH2025】Photographic Conviviality: ボディペイント・ワークショップによる 同時的かつ共生的な写真体験
toremolo72
0
190
ドメイン知識がない領域での自然言語処理の始め方
hargon24
1
260
Aurora Serverless からAurora Serverless v2への課題と知見を論文から読み解く/Understanding the challenges and insights of moving from Aurora Serverless to Aurora Serverless v2 from a paper
bootjp
6
1.5k
湯村研究室の紹介2025 / yumulab2025
yumulab
0
320
Attaques quantiques sur Bitcoin : comment se protéger ?
rlifchitz
0
160
財務諸表監査のための逐次検定
masakat0
1
270
AI Agentの精度改善に見るML開発との共通点 / commonalities in accuracy improvements in agentic era
shimacos
5
1.4k
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
960
ForestCast: Forecasting Deforestation Risk at Scale with Deep Learning
satai
3
490
Featured
See All Featured
Leo the Paperboy
mayatellez
4
1.5k
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
2
500
コードの90%をAIが書く世界で何が待っているのか / What awaits us in a world where 90% of the code is written by AI
rkaga
60
42k
It's Worth the Effort
3n
188
29k
Building a A Zero-Code AI SEO Workflow
portentint
PRO
0
370
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.4k
Impact Scores and Hybrid Strategies: The future of link building
tamaranovitovic
0
220
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
333
22k
Lightning Talk: Beautiful Slides for Beginners
inesmontani
PRO
1
460
A Soul's Torment
seathinner
5
2.4k
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
soudai
PRO
62
51k
The Impact of AI in SEO - AI Overviews June 2024 Edition
aleyda
5
760
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