4 citations · 10 across the 12 of their papers we have counts for
Showing 2026 · cs.LGShow all
3 papers · 2 filters
cs.LG2026
Awakening of the Buddha: Subspace Learning During Population-Loss Plateaus
Akash Kumar
Population loss can remain nearly constant while a neural network learns a substantially more predictive representation. We establish this separation for two-layer ReLU and leaky-R…
cs.LG2026
Can Representation Learning Decouple from Loss Minimization? Polar Updates Have an Answer
Akash Kumar
Does representation learning stop when the training loss stops improving? We study this question for matrix Muon, whose polar-normalised updates have a step length set by the gradi…
cs.LG2026
A Gap Between Decision Trees and Neural Networks
Akash Kumar
We study when geometric simplicity of decision boundaries, used here as a notion of interpretability, can conflict with accurate approximation of axis-aligned decision trees by sha…