Risultati della ricerca - Block, Adam

The Sample Complexity of Approximate Rejection Sampling with Applications to Smoothed Online Learning di Block, Adam, Polyanskiy, Yury

Testo

Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective di Block, Adam, Shetty, Abhishek

Testo

EMA Without the Lag: Bias-Corrected Iterate Averaging Schemes di Block, Adam, Zhang, Cyril

Testo

Partition Function Estimation under Bounded f-Divergence di Block, Adam, Shetty, Abhishek

Testo

Revisiting the (Sub)Optimality of Best-of-N for Inference-Time Alignment di Sriraman, Ved, Block, Adam

Testo

Smoothed Online Learning for Prediction in Piecewise Affine Systems di Block, Adam, Simchowitz, Max, Tedrake, Russ

Testo

Oracle-Efficient Smoothed Online Learning for Piecewise Continuous Decision Making di Block, Adam, Rakhlin, Alexander, Simchowitz, Max

Testo

On the Performance of Empirical Risk Minimization with Smoothed Data di Block, Adam, Rakhlin, Alexander, Shetty, Abhishek

Testo

GaussMark: A Practical Approach for Structural Watermarking of Language Models di Block, Adam, Sekhari, Ayush, Rakhlin, Alexander

Testo

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning di Foster, Dylan J., Block, Adam, Misra, Dipendra

Testo

MarkTune: Improving the Quality-Detectability Trade-off in Open-Weight LLM Watermarking di Zhao, Yizhou, Wu, Zhiwei Steven, Block, Adam

Testo

From Curiosity to Caution: Mitigating Reward Hacking for Best-of-N with Pessimism di Yu, Zhuohao, Wu, Zhiwei Steven, Block, Adam

Testo

Rate of convergence of the smoothed empirical Wasserstein distance di Block, Adam, Jia, Zeyu, Polyanskiy, Yury, Rakhlin, Alexander

Testo

Efficient Model-Free Exploration in Low-Rank MDPs di Mhammedi, Zakaria, Block, Adam, Foster, Dylan J., Rakhlin, Alexander

Testo

Oracle-Efficient Differentially Private Learning with Public Data di Block, Adam, Bun, Mark, Desai, Rathin, Shetty, Abhishek, Wu, Steven

Testo

Computational-Statistical Tradeoffs at the Next-Token Prediction Barrier: Autoregressive and Imitation Learning under Misspecification di Rohatgi, Dhruv, Block, Adam, Huang, Audrey, Krishnamurthy, Akshay, Foster, Dylan J.

Testo

Is Best-of-N the Best of Them? Coverage, Scaling, and Optimality in Inference-Time Alignment di Huang, Audrey, Block, Adam, Liu, Qinghua, Jiang, Nan, Krishnamurthy, Akshay, Foster, Dylan J.

Testo

A Theory of Learning with Autoregressive Chain of Thought di Joshi, Nirmit, Vardi, Gal, Block, Adam, Goel, Surbhi, Li, Zhiyuan, Misiakiewicz, Theodor, Srebro, Nathan

Testo

Self-Improvement in Language Models: The Sharpening Mechanism di Huang, Audrey, Block, Adam, Foster, Dylan J., Rohatgi, Dhruv, Zhang, Cyril, Simchowitz, Max, Ash, Jordan T., Krishnamurthy, Akshay

Testo

The Coverage Principle: How Pre-Training Enables Post-Training di Chen, Fan, Huang, Audrey, Golowich, Noah, Malladi, Sadhika, Block, Adam, Ash, Jordan T., Krishnamurthy, Akshay, Foster, Dylan J.

Testo