Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
Understanding numpyro
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Kazuaki Takehara
October 29, 2022
Research
280
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
Understanding numpyro
numpyro の基本的な使い方から内部構造の把握.
plate, sample, HMC, MCMC の挙動を中心に.
Kazuaki Takehara
October 29, 2022
More Decks by Kazuaki Takehara
See All by Kazuaki Takehara
A brief introduction to tinygp
zak3
0
160
Other Decks in Research
See All in Research
20260624 NLP colloquium: 単一のhubテキストがCLIPを壊す:hubnessによる埋め込みの脆弱性特定
de9uch1
2
280
Source Code Diff Revolution
tsantalis
0
160
【ローカルAIに向き合う展示会vol.2】液体時間定数型モジュールを用いた オリジナルの双方向エンコーダーモデルNexteraBERT 推論速度向上検討並びにダウンストリーム評価
rikkabotan7
0
210
XDPerf: A High-Performance Traffic Generator Built with WASM and eBPF
takehaya
1
310
Easy to Guess, Hard to Verify: Lessons from AIMO 3 for Olympiad-Level AI Mathematics
corochann
0
120
ESTUDIO DE OPINIÓN REALIZADO EN SEPTIEMBRE 2026 EN EL MUNICIPIO DE OAXACA DE JUÁREZ, OAXACA
merca6
0
470
ふとした出会いで生まれたSkillが、 社内利用1位になるまで
mikimhk
22
24k
Vector Map as Language: Toward Unified Remote Sensing Vector Mapping
satai
3
290
HAKARI-Bench - 実運用視点での情報検索モデル評価ベンチマーク
hotchpotch
1
770
最先端NLP勉強会2026 論文紹介:Reasoning with Sampling: Your Base Model is Smarter Than You Think (ICLR 2026 paper)
kogoro
4
640
Evaluation génomique des femelles laitières croisées : comprendre la méthode pour accompagner les éleveurs à son utilisation
institudelelevage
PRO
0
110
Cross-Media Information Spaces and Architectures
signer
PRO
0
380
Featured
See All Featured
The innovator’s Mindset - Leading Through an Era of Exponential Change - McGill University 2025
jdejongh
PRO
1
340
Hiding What from Whom? A Critical Review of the History of Programming languages for Music
tomoyanonymous
3
1.3k
The Art of Delivering Value - GDevCon NA Keynote
reverentgeek
16
2.2k
Mozcon NYC 2025: Stop Losing SEO Traffic
samtorres
1
560
The Psychology of Web Performance [Beyond Tellerrand 2023]
tammyeverts
49
3.6k
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
uxyall
1
420
Documentation Writing (for coders)
carmenintech
77
5.5k
Chrome DevTools: State of the Union 2024 - Debugging React & Beyond
addyosmani
10
1.3k
The Pragmatic Product Professional
lauravandoore
37
7.5k
[RailsConf 2023 Opening Keynote] The Magic of Rails
eileencodes
31
10k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
50
10k
How STYLIGHT went responsive
nonsquared
100
6.3k
Transcript
numpyro Λཧղ͢Δ _zak3 2022/10
Agenda • numpyro ͱ • Πϯετʔϧ • ͍ํͷཧղ • ෦ߏͷཧղ
2
nympyro ͱ • ܰྔͳ֬ϓϩάϥϛϯάϥΠϒϥϦʢPPLʣɽ • jax ϕʔεɽJITίϯύΠϧɼࣗಈඍɼGPU ߴԽʹରԠɽ 3 Github:
https://github.com/pyro-ppl/numpyro
Πϯετʔϧ • pip install --upgrade pip • pip install numpyro
4
͍ํͷཧղ
8 Schools • ίʔνϯά͕ SAT*1 ͷʹ༩͑ΔӨڹʹ͍ͭͯͷσʔλɽ • y : ॲஔޮՌɼsigma
: ඪ४ޡࠩɽ 6 *1: [Wikipedia] SATɺຊདྷScholastic Aptitude TestʢେֶదੑࢼݧʣΛҙຯ͢ΔུޠͰ͕͋ͬͨɺ1990ʹScholastic Assessment TestʢେֶೳྗධՁࢼݧʣʹมΘΓɺݱࡏུͱͯ͠Ͱͳ͘SATͦͷͷ໊͕લʹΘΕ͍ͯΔɻ
ϞσϦϯά • ϞσϧؔͰදݱ͢Δʢ͜͜Ͱ eight_schoolsʣɽ • άϥϑΟΧϧϞσϧͱରൺ͠ͳ͕ΒͩͱΘ͔Γ͍͢ɽ 7
αϯϓϦϯά • mcmc.run ͰαϯϓϦϯάΛ࣮ߦɽ • ͜ͷ࣌ʹϞσϧͷҾࢦఆ͢Δʢ͕͜͜গ͔͠ΓͮΒ͍ʣɽ 8
αϯϓϧͷ֬ೝ (1 / 3) • arviz Λར༻͢Δͱศརɽ • mcmc ͔Β
InferenceData Λऔಘɽ 9
αϯϓϧͷ֬ೝ (2 / 3) • summary 10
αϯϓϧͷ֬ೝ (3 / 3) • trace plot 11
෦ߏͷཧղ plate, sample, NUTS, MCMC ͷϓϩάϥϜతͳڍಈʹ͍ͭͯɽ
plate • খจࣈ͕ͩ Messenger Λܧঝͨ͠Ϋϥεɽ • with ۟Ͱར༻͞ΕΔ context managerɽ
• __enter__, __exit__ Λ࣋ͭɽ • plate ίϯςΩετͰͷ sample ϝιου ϓϨʔταΠζʹϒϩʔυΩϟετ͞ΕΔɽ 13 ར༻ͷ؍Ͱ͜ͷڍಈ͚ͩཧղ͓͚ͯ͠ ྑ͍ͱࢥΘΕΔɽ
Messenger • ؔ fn ΛҾʹΠϯελϯεԽɽ • with ۟ʹೖͬͨͱ͖ɼ __enter__͕࣮ߦ ͞Ε
_PYRO_STACK ʹ appendɽ • with ͔۟Βग़Δͱ͖ɼ __exit__ ͕࣮ߦ ͞Εɼ_PYRO_STACK ͔Β popɽ • process_message / postprocess_message ܧঝઌͰ࣮ɽ 14
primitives.sample • plate ίϯςΩετͰ _PYRO_STACK ͕ଘ ࡏ͢ΔͨΊӈͷͷίʔυ͕࣮ߦ͞ΕΔɽ • apply_stackʹͯ _PYRO_STACK
্Ͱ msg[“fn”] ͕ධՁ͞ΕΔɽ 15 ελοΫ=จ຺ɽ ॲཧΛจ຺ʹΑͬͯΓସ͑Δػߏɽ
apply_stack() • msg dict ܕͷɼhandler Messenger ͷαϒΫϥεͷ Πϯελϯεɽ
• _PYRO_STACK ্ʹɼ plate, trace, substitute, seed ͳͲͷෳͷ handlers ͕ొ͞Ε͍ͯΔɽ • see: https://num.pyro.ai/en/latest/handlers.html • ҎԼͷॱͰ࣮ߦ͞Ε msg[“value”]ͳͲ༷ʑͳใ͕Ճ ͞ΕΔɽ • handler#process_message • default_process_message • hander#postprocess_message 16 see also: Poutine http://pyro.ai/examples/effect_handlers.html
plate#process_message plate#postprocess_message 17 plate ʹࢦఆ͞Εͨ size ͰϒϩʔυΩϟετ͞Ε͍ͯΔՕॴɽ .expand ʹΑΓ Distribution
Ϋϥε͔Β ExpandedDistribution Ϋϥε ʹม͞Ε͍ͯΔɽ
default_process_message • hander#process_message ʹΑΓม͞Εͨ msg[“fn”] ͕࣮ߦ͞ΕΔɽ • msg[“args”], msg[“kwargs”] ͕Ҿɽ
• msg[“value”] ʹฦΓ͕֨ೲ͞ΕΔɽ 18
NUTS • __init__ ͷΈ͕ఆٛ͞Ε͍ͯΔͳͷͰɼ ࣮ଶ HMCɽ 19
HMC • MCMCKernel ͷαϒΫϥεʹͳ͍ͬͯΔɽ • நϝιου init, sample Λ࣮ɽ 20
HMC#init • self._sample_fn ͕ηοτ͞Εɼhmc_init_fn ͷ࣮ߦ݁Ռ init_state ͕ return ͞ΕΔɽ 21
HMC#sample • self._sample_fn Λ࣮ߦ 22
MCMC#run • _single_chain_mcmc ͷҾΛ෦ద༻ͨ͠ partial_map_fn Λ࡞ɽ • num_chains, chain_method ͷछผʹԠͯ͡
partial_map_fn Λ࣮ߦͯ݁͠Ռstates/ last_state Λ֫ಘ͢Δɽ • states : dict ܕ • states[‘z’] ʹύϥϝʔλͷαϯϓϧ͕ ֨ೲ͞Ε͍ͯΔɽ • last_state : HMCState ܕ 23
HMCState • namedtuple Ͱఆٛ͞Ε͍ͯΔɽ 24