44 citations · 159 across the 31 of their papers we have counts for
36 papers
On-the-go Forgetting without Explicit Unlearning via ERASE
Kushal Chakrabarti, Mayank Baranwal
Existing unlearning approaches typically rely on post hoc weight adaptation or distillation, leading to duplicated memory costs, degraded generalization, and limited scalability. I…
SOVER: Formal Certification of Optimization Reformulations via LLM-Assisted SMT Verification
Swapnil Bhattacharyya, Mayank Baranwal
Large Language Models (LLMs) have shown remarkable promise in translating and reformulating complex mathematical optimization problems across modeling languages. However, validatin…
Why Clipping Matters in AdaGrad? Toward a High-Probability Theory under Generalized Smoothness
Alokendu Mazumder, Ayaan Mohd, Harshit Rawat +3
We analyze the original same-step coordinate-wise AdaGrad under generalized smoothness and heavy-tailed noise with bounded variance. In this setting, local curvature may grow sub-q…
Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry
Susmit Sarkar, Abhinav Raghuvanshi, Kushal Chakrabarti +1
We study distributed optimization with stochastic gradients and finite-bit communication modeled by random (unbiased) quantization. We propose q-PDGD, a quantized stochastic primal…
On a Gradient Approach to Chebyshev Center Problems with Applications to Function Learning
Abhinav Raghuvanshi, Mayank Baranwal, Debasish Chatterjee
We introduce , the first gradient-based optimization framework for solving Chebyshev center problems, a fundamental challenge in optimal function learning and geom…
On Linear Convergence of Distributed Stochastic Bilevel Optimization over Undirected Networks via Gradient Aggregation
Ajay Tak, Mayank Baranwal
Many large-scale constrained optimization problems can be formulated as bilevel distributed optimization tasks over undirected networks, where agents collaborate to minimize a glob…