activity
20242026
collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

Modulated learning for private and distributed regression with just a single sample per client device

Praneeth Vepakomma, Amirhossein Reisizadeh, Samuel Horváth +1

This work focuses on the question of learning from a large number of devices with each device holding only a single sample of data. Several real-world applications exist to this on…

cs.LG2026

Learning in the Null Space: Small Singular Values for Continual Learning

Cuong Anh Pham, Praneeth Vepakomma, Samuel Horváth

Alleviating catastrophic forgetting while enabling further learning is a primary challenge in continual learning (CL). Orthogonal-based training methods have gained attention for t…

cs.LG2026

Safety Subspaces are Not Linearly Distinct: A Fine-Tuning Case Study

Kaustubh Ponkshe, Shaan Shah, Raghav Singhal +1

Large Language Models (LLMs) rely on safety alignment to produce socially acceptable responses. However, this behavior is known to be brittle: further fine-tuning, even on benign o…

cs.LG2025

Offline and Online KL-Regularized RLHF under Differential Privacy

Yulian Wu, Rushil Thareja, Praneeth Vepakomma +1

In this paper, we study the offline and online settings of reinforcement learning from human feedback (RLHF) with KL-regularization -- a widely used objective function in large lan…

cs.LG2025

Power Mechanism: Private Tabular Representation Release for Model Agnostic Consumption

Praneeth Vepakomma, Kaustubh Ponkshe

Traditional collaborative learning approaches are based on sharing of model weights between clients and a server. However, there are advantages to resource efficiency through schem…

cs.LG2025

Fed-SB: A Silver Bullet for Extreme Communication Efficiency and Performance in (Private) Federated LoRA Fine-Tuning

Raghav Singhal, Kaustubh Ponkshe, Rohit Vartak +2

Low-Rank Adaptation (LoRA) has become ubiquitous for efficiently fine-tuning foundation models. However, federated fine-tuning using LoRA is challenging due to suboptimal updates a…