Search Results for author:
Found 15 papers, 4 papers with code
Calibrating Multi-modal Representations: A Pursuit of Group Robustness without Annotations
As a piloting study, this work focuses on exploring mitigating the reliance on spurious features for CLIP without using any group annotation.
Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation
We study multi-agent reinforcement learning in the setting of episodic Markov decision processes, where multiple agents cooperate via communication through a central server.
Implicit Anatomical Rendering for Medical Image Segmentation with Stochastic Experts
Integrating high-level semantically correlated contents and low-level anatomical features is of central importance in medical image segmentation.
ACTION++: Improving Semi-supervised Medical Image Segmentation with Adaptive Anatomical Contrast
In this work, we present ACTION++, an improved contrastive learning framework with adaptive anatomical contrast for semi-supervised medical segmentation.
Finding Regularized Competitive Equilibria of Heterogeneous Agent Macroeconomic Models with Reinforcement Learning
We study a heterogeneous agent macroeconomic model with an infinite number of households and firms competing in a labor market.
Mine yOur owN Anatomy: Revisiting Medical Image Segmentation with Extremely Limited Labels
Blindly leveraging all pixels in training hence can lead to the data imbalance issues, and cause deteriorated performance; (2) consistency: it remains unclear whether a segmentation model has learned meaningful and yet consistent anatomical features due to the intra-class variations between different anatomical features; and (3) diversity: the intra-slice correlations within the entire dataset have received significantly less attention.
A Simple and Provably Efficient Algorithm for Asynchronous Federated Contextual Linear Bandits
To the best of our knowledge, this is the first provably efficient algorithm that allows fully asynchronous communication for federated contextual linear bandits, while achieving the same regret guarantee as in the single-agent setting.
Bootstrapping Semi-supervised Medical Image Segmentation with Anatomical-aware Contrastive Distillation
In this work, we present ACTION, an Anatomical-aware ConTrastive dIstillatiON framework, for semi-supervised medical image segmentation.
Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes
We study offline reinforcement learning (RL) in partially observable Markov decision processes.
Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets
We study a Markov matching market involving a planner and a set of strategic agents on the two sides of the market.
Learning Stochastic Shortest Path with Linear Function Approximation
To the best of our knowledge, this is the first algorithm with a sublinear regret guarantee for learning linear mixture SSP.
Variance-Aware Off-Policy Evaluation with Linear Function Approximation
We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on the offline data collected by a behavior policy.
Multiple Descent: Design Your Own Generalization Curve
This paper explores the generalization loss of linear regression in variably parameterized families of models, both under-parameterized and over-parameterized.
The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt Generalization
In the medium adversary regime, with more training data, the generalization loss exhibits a double descent curve, which implies the existence of an intermediate stage where more training data hurts the generalization.
More Data Can Expand the Generalization Gap Between Adversarially Robust and Standard Models
Despite remarkable success in practice, modern machine learning models have been found to be susceptible to adversarial attacks that make human-imperceptible perturbations to the data, but result in serious and potentially dangerous prediction errors.
