activity
20242026
collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2026

Knowing When to Quit: A Principled Framework for Dynamic Abstention in LLM Reasoning

Hen Davidov, Nachshon Cohen, Oren Kalinsky +4

LLMs utilizing chain-of-thought reasoning often waste substantial compute by producing long, incorrect responses. Abstention can mitigate this by withholding outputs unlikely to be…

cs.LG2026

Sharp Risk Bounds for Early-Stopping in Gaussian Linear Regression

Tobias Wegel, Gil Kur, Patrick Rebeschini

We study early-stopped mirror descent (ESMD) for high-dimensional Gaussian linear regression over arbitrary convex bodies and design matrices, where the task is to minimize the in-…

cs.LG2026

On-Average Stability of Multipass Preconditioned SGD and Effective Dimension

Simon Vary, Tyler Farghly, Ilja Kuzborskij +1

We study trade-offs between the population risk curvature, geometry of the noise, and preconditioning on the generalisation ability of the multipass Preconditioned Stochastic Gradi…

cs.LG2026

Meta-Learning Objectives for Preference Optimization

Carlo Alfano, Silvia Sapora, Jakob Nicolaus Foerster +2

Evaluating preference optimization (PO) algorithms on LLM alignment is a challenging task that presents prohibitive costs, noise, and several variables like model size and hyper-pa…

cs.LG2025

On the necessity of adaptive regularisation:Optimal anytime online learning on -balls

Emmeran Johnson, David Martínez-Rubio, Ciara Pike-Burke +1

We study online convex optimization on -balls in for . While always sub-linear, the optimal regret exhibits a shift between the high-dimensional setti…

cs.LG2025

Stochastic Shortest Path with Sparse Adversarial Costs

Emmeran Johnson, Alberto Rumi, Ciara Pike-Burke +1

We study the adversarial Stochastic Shortest Path (SSP) problem with sparse costs under full-information feedback. In the known transition setting, existing bounds based on Online…