Simon Lacoste-Julien

activity

20112026

most citedSAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives

927 citations · 2.7k across the 88 of their papers we have counts for

collaborators

Showing 2026Show all

2 papers · 1 filter

stat.ML2026

Lloyd's $K$ -Means Clustering Algorithm Is Frank-Wolfe in Disguise

Michael Pokojovy, J. Marcus Jobe, Simon Lacoste-Julien

Lloyd's $K$ -means algorithm, also known as naïve $K$ -means, is a widely used ad hoc optimization heuristic, designed to minimize the sum of squared errors (SSE) across all $K$ -part…

cs.LG2026

Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation

Vitória Barin Pacela, Vitória Barin-Pacela, Shruti Joshi +3

The linear representation hypothesis states that neural network activations encode high-level concepts as linear mixtures. However, under superposition, this encoding is a projecti…

Lloyd's K-Means Clustering Algorithm Is Frank-Wolfe in Disguise

Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation

Lloyd's $K$ -Means Clustering Algorithm Is Frank-Wolfe in Disguise