Top-K logit censoring bounds the total-variation diameter of compatible teacher distributions by U_K but permits substantial capability transfer via distillation even when KL divergence is near zero.
A mathematical the- ory of top-k sparse attention via total varia- tion distance
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A tiered KV cache architecture computes per-head per-step error bounds on quantized attention and uses adaptive fallback to guarantee bounded or exact outputs relative to FP16 reference.
citing papers explorer
-
Identified-Set Geometry of Distributional Model Extraction under Top-$K$ Censored API Access
Top-K logit censoring bounds the total-variation diameter of compatible teacher distributions by U_K but permits substantial capability transfer via distillation even when KL divergence is near zero.
-
Runtime-Certified Bounded-Error Quantized Attention
A tiered KV cache architecture computes per-head per-step error bounds on quantized attention and uses adaptive fallback to guarantee bounded or exact outputs relative to FP16 reference.