Training on the Test Set and Other Heresies

Computation in Very Wide Neural Networks

Ben Recht - Splitting the difference between deep and shallow solutions of inverse problems

Bayesian or Frequentist, Which Are You? By Michael I. Jordan (Part 1 of 2)

The Data Addition Dilemma

Mad Max: Affine Spline Insights into Deep Learning

Benjamin Recht: Optimization Perspectives on Learning to Control (ICML 2018 tutorial)

ICLR 2021 Keynote - "Geometric Deep Learning: The Erlangen Programme of ML" - M Bronstein

Improving and Generalizing Flow-Based Generative Models with Minibatch Optimal Transport | Alex Tong

A New Perspective on Adversarial Perturbations

From Classical Statistics to Modern Machine Learning

AI’s Models of the World, and Ours | Theoretically Speaking

Is Optimization the Right Language to Understand Deep Learning? - Sanjeev Arora

ICML 2018: Tutorial Session: Optimization Perspectives on Learning to Control

Distinguished Lecturer Series: Building Science - Adventures in Building Science

Discrete diffusion modeling by estimating the ratios of the data distribution

Bandits, Active Learning, Bayesian RL and Global Optimization - Marc Toussaint - MLSS 2013 Tübingen

Bandit Convex Optimization, PGMO Lecture 1

On the Foundations of Deep Learning: SGD, Overparametrization, and Generalization

The linear bandit problem

«Когда мы что-то видим, мы всегда что-то не видим» // «Скажи Гордеевой»