Antonio Silveti-Falls — accepted AI-conference papers

2026

On the Role of Batch Size in Stochastic Conditional Gradient Methods

Rustem Islamov, Roman Machacek, Aurelien Lucchi, Antonio Silveti-Falls, Eduard Gorbunov, Volkan Cevher

ICML 2026poster

We study the role of batch size in stochastic conditional gradient methods under a $\mu$-Kurdyka–Łojasiewicz ($\mu$-KL) condition. Focusing on momentum-based stochastic Frank–Wolfe–type conditional gradient algorithms (e.g., Scion), we derive a new analysis that explicitly captures the interaction b…

Cited by 0 Source ↗Scholar ↗

2025

Training Deep Learning Models with Norm-Constrained LMOs

Thomas Pethick, Wanyun Xie, Kimon Antonakopoulos, Zhenyu Zhu, Antonio Silveti-Falls, Volkan Cevher

ICML 2025spotlight

In this work, we study optimization methods that leverage the linear minimization oracle (LMO) over a norm-ball. We propose a new stochastic family of algorithms that uses the LMO to adapt to the geometry of the problem and, perhaps surprisingly, show that they can be applied to unconstrained proble…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2021

Nonsmooth Implicit Differentiation for Machine-Learning and Optimization

Jerome Bolte, Tam Le, Edouard Pauwels, Antonio Silveti-Falls

NeurIPS 2021poster

In view of training increasingly complex learning architectures, we establish a nonsmooth implicit function theorem with an operational calculus. Our result applies to most practical problems (i.e., definable problems) provided that a nonsmooth form of the classical invertibility condition is fulfil…

Cited by 76 Source ↗PDF ↗Scholar ↗