technique
Frank-Wolfe Optimization
techniqueactiveprovisional
frank-wolfe-optimization-2af5e689·1 events·first seen 19d agoAliases: Frank-Wolfe Optimization
Co-occurring entities
More like this (12)
distributed optimizationBiconvex OptimizationBayesian OptimizationVector Policy OptimizationMuon OptimizerPareto Optimal Policy OptimizationPrivate Stochastic Convex OptimizationFine-Tuning for Financial UtilityGravity-Weighted Direct Preference Optimizationorthogonal finetuningoptimization theorydifferentiable convex optimization
Recent events (1)
HullFT: Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching
HullFT is a new method for test-time finetuning (TTFT) of language models that addresses the dual bottlenecks of retrieval quality and per-query finetuning cost. It represents query embeddings as sparse convex combinations of training sequences using Frank-Wolfe optimization, yielding diverse and relevant support sets without expensive diversity-aware search. A geometric integerization step converts fractional weights into integer multiplicities, enabling a Gradient Reuse scheme that amortizes forward-backward computation across repeated examples. Experiments show improved quality-efficiency tradeoffs over prior TTFT methods, measured in bits-per-byte at lower total runtime.