🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

「Play with me!」（by Everyday One Cat）#motiongnyaphics #EveOneCat

Pair programming

“I’m trying to apply deep learning inside my company.”

1/ Excited to share something I've been working on for a while now. Troubleshooting Deep Neural Networks: a decision tree for debugging your model and improving performance. josh-tobin.com/troubleshootin…

This is really neat! You take a screenshot of an equation, it gives you the LaTeX code, you can directly modify in the taskbar, copy, paste, done. mathpix.com

After a 2 year break, I'll be teaching in the fall a grad course. Go Bandits! banditalgs.com

Looking back over the year, the one paper that gave me the best "aha" moment was... Reconciling Modern Machine Learning and the Bias-Variance Tradeoff: arxiv.org/abs/1812.11118 The "bias-variance" you knew was just the first piece of the story!

This is my favorite tweet of all time 🙂I got quite a few new followers so thought I'd share it with you One thing I would add is that `l` and `ll` give you context around the line where exception was raised.

"Behind every great theorem lies a great inequality" This inequalities cheat sheet has been really helpful to keep on hand while working - passing it along in case others find it useful lkozma.net/inequalities_c… lkozma.net/inequalities_c…

"Finite Versus Infinite Neural Networks: an Empirical Study." arxiv.org/abs/2007.15801 This paper contains everything you ever wanted to know about infinite width networks, but didn't have the computational capacity to ask! Like really a lot of content. Let's dive in.

1/6 Excited to announce that a draft of my book Algorithms for Convex Optimization (to be published by Cambridge) is available for download: convex-optimization.github.io Intended audience includes undergraduates, graduates and researches from TCS, optimization, and machine learning

Stuff I wish I had known sooner: "Pinsker's inequality is cancelled," a thread. 🧵 If you want to relate total variation (TV) and Kullback-Leibler divergence (KL), then everyone, from textbooks to Google, will point you to Pinsker's inequality: TV(p,q) ≤ √(½ KL(p||q) ) 1/

The #ICML2021 paper of Lam Chi Thanh (Steve) @nghiaht87 Bryan Kian Hsiang Low patrick jaillet proposes model fusion for personalized learning #MetaLearning #FederatedLearning. Paper: proceedings.mlr.press/v139/lam21a.ht… Check us out @ icml.cc/virtual/2021/s…

🧵Fields medalist June Huh shares an early math experience: a chess puzzle in the game "The 11th Hour." Story and figures from nytimes.com/live/2022/07/0…. Can you swap the positions of the black and white knights? Seems hard, right? A new perspective makes it almost trivial! 1/n

The #ICLR2023 work of Lam Chi Thanh (Steve) Arun Verma Bryan Kian Hsiang Low patrick jaillet proposes a risk-aware #ReinforcementLearning algorithm with coherent risk measures and sublinear regret guarantee. Paper: openreview.net/pdf?id=-RwZOVy… Presentation: iclr.cc/virtual/2023/p…