17 papers
Dynamic estimation of slowly varying sequences
Prashant Gokhale, Mikhail Khodak, Sandeep Silwal
We consider the problem of sequentially approximating functions of each element in a slowly-varying sequence, i.e. one where the magnitude of the difference between the elem…
How fast can you find a good hypothesis?
Anders Aamand, Maryam Aliakbarpour, Justin Y. Chen +1
In the hypothesis selection problem, we are given sample and query access to finite set of candidate distributions (hypotheses), , and samples f…
Compact Geometric Representations of Hierarchies
Prashant Gokhale, Piotr Indyk, Yuhao Liu +3
Computing geometric representations of data is a cornerstone of modern machine learning, typically achieved by training dual encoders which map queries and documents into a shared…
Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
Fangzhou Wu, Sandeep Silwal, Qiuyi Zhang
Query clustering organizes queries into groups that reflect shared latent capability demands, enabling capability-aware LLM evaluation. Existing clustering methods, which primarily…
DynMuon: A Dynamic Spectral Shaping View of Muon
Fangzhou Wu, Rikhav Shah, Sandeep Silwal +1
In recent years, Muon has emerged as the dominant method for training large language models, and transformers more broadly. The essential difference, when compared to standard grad…
Adversarially Robust Approximate Furthest Neighbor
Kiarash Banihashem, Jeff Giliberti, Prashant Gokhale +5
We work in the adaptive query model, where one is given a point set and seeks to construct a data structure that can answer correctly and efficiently a seq…