7 papers
SoftWater: Class-Aware Rate Allocation for Softmax Quantization
Joao V. Cavalcanti, Ashia C. Wilson
Post-training quantization pipelines routinely leave the softmax output layer in high precision. Yet in small LLMs with modern vocabularies, the head holds 15--30\% of all paramete…
Adaptive Kernel Selection for Stein Variational Gradient Descent
Moritz Melcher, Simon Weissmann, Ashia C. Wilson +1
A central challenge in Bayesian inference is efficiently approximating posterior distributions. Stein Variational Gradient Descent (SVGD) is a popular variational inference method…
Adaptive Acceleration Without Strong Convexity Priors Or Restarts
Joao V. Cavalcanti, Laurent Lessard, Ashia C. Wilson
A longstanding challenge in optimization is achieving optimal performance when the strong convexity parameter m is unknown. In this paper, we propose NAG-free, a simple extension o…
Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
Vinith M. Suriyakumar, Rohan Alur, Ayush Sekhari +2
Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make increm…
Aligning Evaluation with Clinical Priorities: Calibration, Label Shift, and Error Costs
Gerardo A. Flores, Alyssa H. Smith, Julia A. Fukuyama +1
Machine learning-based decision support systems are increasingly deployed in clinical settings, where probabilistic scoring functions are used to inform and prioritize patient mana…
Semivalue-based data valuation is arbitrary and gameable
Hannah Diehl, Ashia C. Wilson
The game-theoretic notion of the semivalue offers a popular framework for credit attribution and data valuation in machine learning. Semivalues have been proposed for a variety of…