9 papers
The Asymptotics of Language Model Alignment with Memory
Haricharan Balasundaram, V. Arvind Rameshwar
Language model (LM) alignment broadly aims to perturb a given LM into an aligned LM such that i) the outputs produced by and are 'close' in probability, ii) has…
Lower Bound on the Cumulative Constrained Violation for the OGD+Projection algorithm for Constrained Online Convex Optimization (COCO)
Haricharan Balasundaram, Karthick Krishna Mahendran, Rahul Vaze
The problem of constrained online convex optimization is considered, where at each round, once a learner commits to an action , a convex l…
Semantic Smoothing for Language Models via Distribution Estimation and Embeddings
Haricharan Balasundaram, Swathi Shree Narashiman, Pranay Mathur +1
We propose semantic smoothing, a smoothing method for language models that uses embeddings to share statistical observations across semantically similar contexts. The starting poin…
Convex Optimization with Nested Evolving Feasible Sets
Karthick Krishna M., Haricharan Balasundaram, Rahul Vaze
\emph{Convex Optimization with Nested Evolving Feasible Sets (CONES)} is considered where the objective function \(f\) remains fixed but the feasible region evolves over time as a…
Breaking the Cumulative Constraint Violation Barrier while Achieving Static Regret in Constrained Online Convex Optimization
Haricharan Balasundaram, Karthick Krishna Mahendran, Rahul Vaze
The problem of constrained online convex optimization is considered, where at each round, once a learner commits to an action , a convex l…
Distribution Estimation with Side Information
Haricharan Balasundaram, Andrew Thangaraj
We consider the classical problem of discrete distribution estimation using i.i.d. samples in a novel scenario where additional side information is available on the distribution. I…
Learning to Transmit Over Unknown Erasure Channels with Empirical Erasure Rate Feedback
Haricharan Balasundaram, Krishna Jagannathan
We address the problem of reliable data transmission within a finite time horizon over a binary erasure channel with unknown erasure probability. We consider a feedback model w…
Stability Notions for Hospital Residents with Sizes
Haricharan Balasundaram, J B Krishnashree, Girija Limaye +1
The Hospital Residents problem with sizes (HRS) is a generalisation of the well-studied hospital residents (HR) problem. In the HRS problem, an agent a has a size s(a) and the agen…
Generalized Capacity Planning for the Hospital-Residents Problem
Haricharan Balasundaram, Girija Limaye, Meghana Nasre +1
The Hospital Residents setting models important problems like school choice, assignment of undergraduate students to degree programs, among many others. In this setting, fixed quot…