collaborators

9 papers

cs.AI2026

The Abstention Protocol: RCA for Clos Fabrics

Madhava Gaikwad, Deepak Pandey

Root cause analysis (RCA) in large datacenter networks is challenging because telemetry is noisy, partial, and asynchronous. Score-based approaches degrade under these conditions,…

cs.LG2026

Algorithmic Analysis of Dense Associative Memory: Finite-Size Guarantees and Adversarial Robustness

Madhava Gaikwad

Dense Associative Memory (DAM) generalizes Hopfield networks through higher-order interactions and achieves storage capacity that scales as under suitable pattern sepa…

cs.AI2026

Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents

Madhava Gaikwad

Memory-augmented agents maintain multiple specialized stores, yet most systems retrieve from all stores for every query, increasing cost and introducing irrelevant context. We form…

cs.LG2026

When Are Two RLHF Objectives the Same?

Madhava Gaikwad

The preference optimization literature contains many proposed objectives, often presented as distinct improvements. We introduce Opal, a canonicalization algorithm that determines…

cs.CR2025

AlignDP: Hybrid Differential Privacy with Rarity-Aware Protection for LLMs

Madhava Gaikwad

Large language models are exposed to risks of extraction, distillation, and unauthorized fine-tuning. Existing defenses use watermarking or monitoring, but these act after leakage.…

cs.AI2025

Murphys Laws of AI Alignment: Why the Gap Always Wins

Madhava Gaikwad

We study reinforcement learning from human feedback under misspecification. Sometimes human feedback is systematically wrong on certain types of inputs, like a broken compass that…