Publications & Preprints

The publications and preprints are sorted chronologically. For the most updated list, see my Google Scholar.

Publications

1. Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
   Adam Block, Dylan J. Foster, Akshay Krishnamurthy, Max Simchowitz, and Cyril Zhang. arxiv
   ICLR 2024
   

2. Smoothed Online Learning for Prediction in Piecewise Affine Systems
   Adam Block, Max Simchowitz, and Russ Tedrake. arxiv
   Neurips 2023 (Spotlight)
   

3. Efficient Model-Free Exploration in Low-Rank MDPs
   Zak Mhammedi, Adam Block, Dylan Foster, and Alexander Rakhlin. arxiv
   NeurIPS 2023
   

4. On the Imitation of Non-Markovian Demonstrations: From Low-Level Stability to High Level Planning
   Adam Block, Ali Jadbabaie, Daniel Pfrommer, Max Simchowitz, and Russ Tedrake. arxiv
   NeurIPS 2023
   Workshop on Optimal Transport in Learning, Control, and Dynamical Systems, ICML 2023
   

5. Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making
   Adam Block, Max Simchowitz, and Alexander Rakhlin. COLT 2023. arxiv

6. The Sample Complexity of Approximate Rejection Sampling With Applications to Smoothed Online Learning
   Adam Block and Yury Polyanskiy. COLT 2023. arxiv

7. Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions
   Adam Block and Max Simchowitz. NeurIPS 2022. arxiv

8. Intrinsic Dimension Estimation using Wasserstein Distance
   Adam Block, Zeyu Jia, Yury Polyanskiy, and Alexander Rakhlin. Journal of Machine Learning Research (Accepted 2022). arxiv

9. Smoothed Online Learning is as Easy as Statistical Learning
   Adam Block, Yuval Dagan, Noah Golowich, and Alexander Rakhlin. COLT 2022. arxiv

10. Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion
    Adam Block, Rahul Kidambi, Thorsten Joachims, Daniel N. Hill, and Inderjit S. Dhillon. SIGIR 2022. arxiv

11. Majorizing Measures, Sequential Complexities, and Online Learning
    Adam Block, Yuval Dagan, and Alexander Rakhlin. COLT 2021. arxiv

Preprints

1. On the Performance of Empirical Risk Minimization with Smoothed Data
   Adam Block, Alexander Rakhlin, and Abhishek Shetty. arxiv

2. Oracle-Efficient Differentially Private Learning with Public Data
   Adam Block, Mark Bun, Rathin Desai, Abhishek Shetty, and Zhiwei Steven Wu. arxiv

3. Rate of Convergence of the Smoothed empirical Wasserstein Distance
   Adam Block, Zeyu Jia, Yury Polyanskiy, and Alexander Rakhlin. arxiv

4. Fast mixing of multi-scale langevin dynamics underthe manifold hypothesis
   Adam Block, Youssef Mroueh, Jerret Ross, and Alexander Rakhlin. arxiv

5. Generative modeling with denoising auto-encoders and Langevin sampling
   Adam Block, Youssef Mroueh, and Alexander Rakhlin. arxiv