Going to ICML 2024 ? Here is a curated list of papers related to my research interests. Feel free to suggest additions !

Learning Theory

Asymmetry in Low-Rank Adapters of Foundation Models

How do Transformers Perform In-Context Autoregressive Learning ?

Keep the Momentum: Conservation Laws beyond Euclidean Gradient Flows

How Smooth is Attention ?

Differentiable Distributionally Robust Optimization Layers

DOGE: Domain Reweighting with Generalization Estimation

Slicing Mutual Information Generalization Bounds for Neural Networks

Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation

Generalization Bounds for Causal Regression: Insights, Guarantees and Sensitivity Analysis

From Generalization Analysis to Optimization Designs for State Space Models

Privacy

Privacy-Preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent

Provable Privacy with Non-Private Pre-Processing

Privacy Preserving Adaptative Experiment Design

Shifted Interpolation for Differential Privacy

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

Privacy Attacks in Decentralized Learning

Applications

CARTE: Pretraining and Transfer for Tabular Learning

Survival Kernets: Scalable and Interpretable Deep Kernel Survival Analysis with an Accuracy Guarantee

A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization

Reservoir Computing for Short High-Dimensional Time Series: an Application to SARS-CoV-2 Hospitalization Forecast

SAMformer: Unlocking the Potential of Transformers in Time Series Forecasting with Sharpness-Aware Minimization and Channel-Wise Attention

On The Fairness Impacts of Hardware Selection in Machine Learning

Position: Measure Dataset Diversity, Don't Just Claim It

Position: On the Societal Impact of Open Foundation Models