Vertex-Softmax computes the tightest sound bounds on softmax from pre-softmax score intervals alone via vertex optimization with log-linear complexity and is proven optimal for interval-only information.
International Conference on Learning Representations , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2representative citing papers
The output error from fully convex-relaxed neural network verification grows exponentially with depth and linearly with input radius, with misclassification probability showing step-like dependence on radius.
citing papers explorer
-
Vertex-Softmax: Tight Transformer Verification via Exact Softmax Optimization
Vertex-Softmax computes the tightest sound bounds on softmax from pre-softmax score intervals alone via vertex optimization with log-linear complexity and is proven optimal for interval-only information.
-
The Cost of Relaxation: Evaluating the Error in Convex Neural Network Verification
The output error from fully convex-relaxed neural network verification grows exponentially with depth and linearly with input radius, with misclassification probability showing step-like dependence on radius.