Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Hidden not Deleted: How Networks Suppress Entangled Features
Akash Samanta, Manish Pratap Singh, Debasis Chaudhuri
Concept erasure methods that operate via linear projection assume that features occupy separable subspaces. We show this assumption fails under dense superposition: when two featur…
cs.LG2026
CCAR: Intrinsic Robustness as an Emergent Geometric Property
Akash Samanta, Manish Pratap Singh, Debasis Chaudhuri
Standard supervised learning optimizes for predictive accuracy but remains agnostic to the internal geometry of learned features, often yielding representations that are entangled…
cs.LG2026
Adaptive Learning Guided by Bias-Noise-Alignment Diagnostics
Akash Samanta, Sheldon Williamson
Learning systems deployed in nonstationary and safety-critical environments often suffer from instability, slow convergence, or brittle adaptation when learning dynamics evolve ove…