Adam Block

According to our database, Adam Block authored at least 32 papers between 2020 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism.

Zhuohao Yu, Zhiwei Steven Wu, Adam Block

CoRR, April, 2026

Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment.

Ved Sriraman, Adam Block

CoRR, March, 2026

Partition Function Estimation under Bounded f-Divergence.

Adam Block, Abhishek Shetty

CoRR, February, 2026

2025

MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking.

Yizhou Zhao, Zhiwei Steven Wu, Adam Block

CoRR, December, 2025

The Coverage Principle: How Pre-Training Enables Post-Training.

Fan Chen, Audrey Huang, Noah Golowich, Sadhika Malladi, Adam Block, Jordan T. Ash, Akshay Krishnamurthy, Dylan J. Foster

CoRR, October, 2025

EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes.

Adam Block, Cyril Zhang

CoRR, August, 2025

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification.

Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan J. Foster

CoRR, February, 2025

Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective.

Adam Block, Abhishek Shetty

CoRR, February, 2025

Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment.

Audrey Huang, Adam Block, Qinghua Liu, Nan Jiang, Akshay Krishnamurthy, Dylan J. Foster

Proceedings of the Forty-second International Conference on Machine Learning, 2025

GaussMark: A Practical Approach for Structural Watermarking of Language Models.

Adam Block, Alexander Rakhlin, Ayush Sekhari

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Self-Improvement in Language Models: The Sharpening Mechanism.

Audrey Huang, Adam Block, Dylan J. Foster, Dhruv Rohatgi, Cyril Zhang, Max Simchowitz, Jordan T. Ash, Akshay Krishnamurthy

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification (extended abstract).

Dhruv Rohatgi, Adam Block, Audrey Huang, Akshay Krishnamurthy, Dylan J. Foster

Proceedings of the Thirty Eighth Annual Conference on Learning Theory, 2025

A Theory of Learning with Autoregressive Chain of Thought.

Nirmit Joshi, Gal Vardi, Adam Block, Surbhi Goel, Zhiyuan Li, Theodor Misiakiewicz, Nathan Srebro

Proceedings of the Thirty Eighth Annual Conference on Learning Theory, 2025

2024

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning.

Dylan J. Foster, Adam Block, Dipendra Misra

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Oracle-Efficient Differentially Private Learning with Public Data.

Adam Block, Mark Bun, Rathin Desai, Abhishek Shetty, Zhiwei Steven Wu

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression.

Adam Block, Dylan J. Foster, Akshay Krishnamurthy, Max Simchowitz, Cyril Zhang

Proceedings of the Twelfth International Conference on Learning Representations, 2024

On the Performance of Empirical Risk Minimization with Smoothed Data.

Adam Block, Alexander Rakhlin, Abhishek Shetty

Proceedings of the Thirty Seventh Annual Conference on Learning Theory, June 30, 2024

2023

Imitating Complex Trajectories: Bridging Low-Level Stability and High-Level Behavior.

Adam Block, Daniel Pfrommer, Max Simchowitz

CoRR, 2023

Efficient Model-Free Exploration in Low-Rank MDPs.

Zakaria Mhammedi, Adam Block, Dylan J. Foster, Alexander Rakhlin

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Smoothed Online Learning for Prediction in Piecewise Affine Systems.

Adam Block, Max Simchowitz, Russ Tedrake

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior.

Adam Block, Ali Jadbabaie, Daniel Pfrommer, Max Simchowitz, Russ Tedrake

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making.

Adam Block, Max Simchowitz, Alexander Rakhlin

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

The Sample Complexity of Approximate Rejection Sampling With Applications to Smoothed Online Learning.

Adam Block, Yury Polyanskiy

Proceedings of the Thirty Sixth Annual Conference on Learning Theory, 2023

2022

Intrinsic Dimension Estimation Using Wasserstein Distance.

Adam Block, Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin

J. Mach. Learn. Res., 2022

Rate of convergence of the smoothed empirical Wasserstein distance.

Adam Block, Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin

CoRR, 2022

Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion.

Adam Block, Rahul Kidambi, Daniel N. Hill, Thorsten Joachims, Inderjit S. Dhillon

Proceedings of the SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Madrid, Spain, July 11, 2022

Efficient and Near-Optimal Smoothed Online Learning for Generalized Linear Functions.

Adam Block, Max Simchowitz

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Smoothed Online Learning is as Easy as Statistical Learning.

Adam Block, Yuval Dagan, Noah Golowich, Alexander Rakhlin

Proceedings of the Conference on Learning Theory, 2-5 July 2022, London, UK., 2022

2021

Intrinsic Dimension Estimation.

Adam Block, Zeyu Jia, Yury Polyanskiy, Alexander Rakhlin

CoRR, 2021

Majorizing Measures, Sequential Complexities, and Online Learning.

Adam Block, Yuval Dagan, Alexander Rakhlin

Proceedings of the Conference on Learning Theory, 2021

2020

Fast Mixing of Multi-Scale Langevin Dynamics under the Manifold Hypothesis.

Adam Block, Youssef Mroueh, Alexander Rakhlin, Jerret Ross

CoRR, 2020

Generative Modeling with Denoising Auto-Encoders and Langevin Sampling.

Adam Block, Youssef Mroueh, Alexander Rakhlin

CoRR, 2020