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
780
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
2026年1月の生成AI領域の重要リリース&トピック解説
kajikent
0
850
Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities
satai
3
650
AIを叩き台として、 「検証」から「共創」へと進化するリサーチ
mela_dayo
0
160
[Devfest Incheon 2025] 모두를 위한 친절한 언어모델(LLM) 학습 가이드
beomi
2
1.5k
CyberAgent AI Lab研修 / Social Implementation Anti-Patterns in AI Lab
chck
6
4.1k
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
空間音響処理における物理法則に基づく機械学習
skoyamalab
0
240
Can We Teach Logical Reasoning to LLMs? – An Approach Using Synthetic Corpora (AAAI 2026 bridge keynote)
morishtr
1
170
一般道の交通量減少と速度低下についての全国分析と熊本市におけるケーススタディ(20251122 土木計画学研究発表会)
trafficbrain
0
180
湯村研究室の紹介2025 / yumulab2025
yumulab
0
320
Collective Predictive Coding and World Models in LLMs: A System 0/1/2/3 Perspective on Hierarchical Physical AI (IEEE SII 2026 Plenary Talk)
tanichu
1
310
社内データ分析AIエージェントを できるだけ使いやすくする工夫
fufufukakaka
1
970
Featured
See All Featured
Visual Storytelling: How to be a Superhuman Communicator
reverentgeek
2
470
Understanding Cognitive Biases in Performance Measurement
bluesmoon
32
2.8k
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.7k
Rebuilding a faster, lazier Slack
samanthasiow
85
9.4k
Color Theory Basics | Prateek | Gurzu
gurzu
0
260
How People are Using Generative and Agentic AI to Supercharge Their Products, Projects, Services and Value Streams Today
helenjbeal
1
140
Imperfection Machines: The Place of Print at Facebook
scottboms
269
14k
Designing Powerful Visuals for Engaging Learning
tmiket
0
290
Connecting the Dots Between Site Speed, User Experience & Your Business [WebExpo 2025]
tammyeverts
11
860
Ethics towards AI in product and experience design
skipperchong
2
230
Large-scale JavaScript Application Architecture
addyosmani
515
110k
Max Prin - Stacking Signals: How International SEO Comes Together (And Falls Apart)
techseoconnect
PRO
0
120
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