Author

Peter Richtárik

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

A Sharper Theory of Ball-Proximal Optimization: Convergence and Radius Selection

We study the exact Euclidean ball-proximal point method for proper, closed, convex functions, where each iteration minimizes the objective over a ball centered at the current point. Retaining the objective gap in the decrease of squared distance yields sharper bounds on objective values, stationarity, and the symmetric...

Peter Richtárik, Han-Min Li · 0 citations

#machine learning Preprint May 2026

Broximal Gradient Descent: A Projection-Free Sister of Projected Gradient Descent

BroxGD is proposed, a projection-free sister method to projected gradient descent for constrained optimization for constrained optimization that expects to find many applications and inspire numerous extensions, much like projected gradient descent.

Peter Richtárik, Kaja Gruntkowska, Han-Min Li · 0 citations

#machine learning Preprint Sep 2026

Local LMO is Secretly a Projection Method!

It is shown that, whenever the ball radius does not exceed the Polyak radius, the Local LMO step is the Euclidean projection of the current iterate onto the intersection of the feasible set with a half-space that separates the iterate from the solution set; this projection is nonetheless computable by a linear oracle a...

Peter Richtárik, Ammar Mahran · 0 citations