COLT 2022
153 papers
Top Research Directions
Research directions most represented by COLT 2022 papers.
Top Authors
Impactful Papers
Papers from COLT 2022 that shaped research clusters.
Foundational
Offline Reinforcement Learning: Fundamental Barriers for Value Function Approximation
foundational
Why Realizability and Coverage Fail in O
Neural Networks can Learn Representations with Gradient Descent
foundational
Directional Alignment of Neuron Weights
Beyond No Regret: Instance-Dependent PAC Reinforcement Learning
foundational
Instance-Dependent Complexity and the Su
Influential
Strong Memory Lower Bounds for Learning Natural Models
influential
Proving Streaming Space Lower Bounds via
Memorize to generalize: on the necessity of interpolation in high dimensional linear regression
influential
The Mechanics of Benign Overfitting in H
Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation
influential
How Gradient Descent Selects Simple Solu
The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of spars
influential
Why Gradient Descent Fails on Symmetric
How catastrophic can catastrophic forgetting be in linear regression?
influential
Task Order Sensitivity in Continual Lear
Mirror Descent Strikes Again: Optimal Stochastic Convex Optimization under Infinite Noise Variance
influential
Stochastic Optimization under Heavy Tail
A Sharp Memory-Regret Trade-off for Multi-Pass Streaming Bandits
influential
Fundamental Limits of Memory Constrained
Multi-Agent Learning for Iterative Dominance Elimination: Formal Barriers and New Algorithms
influential
Multi-Agent Learning Under Bandit Feedba
Papers
| Title |
|---|
| Wasserstein GANs with Gradient Penalty Compute Congested Transport |
| When Is Partially Observable Reinforcement Learning Not Scary? |
| Width is Less Important than Depth in ReLU Neural Networks |
« prev Page 4/4