5 papers
Value-Guided KV Compression for LLMs via Approximated CUR Decomposition
Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty
Key-value (KV) cache compression has emerged as a critical technique for reducing the memory and latency overhead of autoregressive language models during inference. Prior approach…
Order-preserving unique Hahn-Banach extensions
Tanmoy Paul, T. S. S. R. K. Rao
Let be a real Banach lattice with a unit, and let be a closed subspace containing the unit. In this paper, we study the order-theoretic (also isometric) structu…
You Only Prune Once: Designing Calibration-Free Model Compression With Policy Learning
Ayan Sengupta, Siddhant Chaudhary, Tanmoy Chakraborty
The ever-increasing size of large language models (LLMs) presents significant challenges for deployment due to their heavy computational and memory requirements. Current model prun…
-Fair Contextual Bandits
Siddhant Chaudhary, Abhishek Sinha
Contextual bandit algorithms are at the core of many applications, including recommender systems, clinical trials, and optimal portfolio selection. One of the most popular problems…
Online Subset Selection using -Core with no Augmented Regret
Sourav Sahoo, Siddhant Chaudhary, Samrat Mukhopadhyay +1
We revisit the classic problem of optimal subset selection in the online learning set-up. Assume that the set consists of distinct elements. On the th round, an advers…