18 papers
From Non-Convex to Strongly Convex: Curvature-Adaptive FTPL for Online Optimization
Moses Charikar, Chirag Pabbaraju, Ambuj Tewari
Curvature adaptivity is a classical theme in online optimization: for convex Lipschitz losses, adaptive methods interpolate between the optimal regret for general con…
Is Zero-Shot Super-Resolution Possible in Operator Learning?
Unique Subedi, Ambuj Tewari
Neural operators are often reported to exhibit zero-shot super-resolution, a phenomenon in which a model trained on coarse grids produces accurate predictions on finer testing grid…
Compute Aligned Training: Optimizing for Test Time Inference
Adam Ousherovitch, Ambuj Tewari
Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-training paradigms, Supervised Fine-Tunin…
Online Conformal Prediction: Enforcing monotonicity via Online Optimization
Eduardo Ochoa Rivera, Ambuj Tewari
Conformal prediction provides a principled framework for uncertainty quantification with finite-sample coverage guarantees. While recent work has extended conformal prediction to o…
Characterizing the Multiclass Learnability of Forgiving 0-1 Loss Functions
Jacob Trauger, Tyson Trauger, Ambuj Tewari
In this paper we will give a characterization of the learnability of forgiving 0-1 loss functions in the multiclass setting with effectively finite cardinality of the output and la…
If generative AI is the answer, what is the question?
Ambuj Tewari
Beginning with text and images, generative AI has expanded to audio, video, computer code, and molecules. Yet, if generative AI is the answer, what is the question? We explore the…