Ali Kavis (2023) ‒ LIONS ‐ EPFL

Research Interests:

Machine Learning
Convex Optimization

Biographie

Ali received his Bachelor’s Degree from Computer Engineering Department of Bilkent University, Turkey, in 2017. On September 2017, he started as a doctoral assistant at EPFL. As of March 2018, I have been a part of LIONS.

Publications with LIONS

Warning

Please note that the publication lists from Infoscience integrated into the EPFL website, lab or people pages are frozen following the launch of the new version of platform. The owners of these pages are invited to recreate their publication list from Infoscience. For any assistance, please consult the Infoscience help or contact support.

Alternation makes the adversary weaker in two-player games

V. Cevher; A. Cutkosky; A. Kavis; G. Piliouras; E. P. Skoulakis et al.

2023. 37th Conference on Neural Information Processing Systems (NeurIPS 2023), New Orlean, USA, December 10-16. 2023.

Detailed record

Full text

Universal and adaptive methods for robust stochastic optimization

A. Kavis / V. Cevher (Dir.)

Lausanne, EPFL, 2023.

Detailed record

Full text – View at publisher

Adaptive Stochastic Variance Reduction for Non-convex Finite-Sum Minimization

A. Kavis; E. P. Skoulakis; K. Antonakopoulos; L. T. Dadi; V. Cevher

2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, Louisianna, USA, November 28-December 9, 2022.

Detailed record

Full text

Extra Newton: A First Approach to Noise-Adaptive Accelerated Second-Order Methods

K. Antonakopoulos; A. Kavis; V. Cevher

2022. 36th Conference on Neural Information Processing Systems (NeurIPS), New Orleans, Louisianna, USA, November 28-December 9, 2022.

Detailed record

Full text

High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize

A. Kavis; K. Levy; V. Cevher

2022. 10th International Conference on Learning Representations (ICLR), Virtual, April 25-29, 2022.

Detailed record

Full text

Sifting through the Noise: Universal First-Order Methods for Stochastic Variational Inequalities

K. Antonakopoulos; T. M. Pethick; A. Kavis; P. Mertikopoulos; V. Cevher

2021. NeurIPS 2021 : Thirty-fifth Conference on Neural Information Processing Systems, Sydney, Australia [Virtual only], December 6-14, 2021.

Detailed record

Full text

STORM+: Fully Adaptive SGD with Momentum for Nonconvex Optimization

K. Levy; A. Kavis; V. Cevher

2021. 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Sydney, Australia, December 6-14, 2021.

Detailed record

Full text

On the Almost Sure Convergence of Stochastic Gradient Descent in Non-Convex Problems

P. Mertikopoulos; N. Hallak; A. Kavis; V. Cevher

2020. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Virtual, December 6-12, 2020.

Detailed record

Full text

Double-Loop Unadjusted Langevin Algorithm

P. Rolland; A. Eftekhari; A. Kavis; V. Cevher

2020. 37th International Conference on Machine Learning (ICLM 2020), Virtual, July 12-18, 2020.

Detailed record

Full text

UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization

A. Kavis; K. Y. Levy; F. Bach; V. Cevher

2019. 33rd Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, December 8-14, 2019.

Detailed record

Full text

Efficient learning of smooth probability functions from Bernoulli tests with guarantees.

P. T. Y. Rolland; A. Kavis; A. Immer; A. Singla; V. Cevher

2019. 36th International Conference on Machine Learning (ICML 2019), Long Beach, USA, June 9-15, 2019.

Detailed record

Full text

Mirrored Langevin Dynamics

Y-P. Hsieh; A. Kavis; P. T. Y. Rolland; V. Cevher

2018. Thirty-second Conference on Neural Information Processing Systems (NIPS), Montréal, p. 2878-2887.

Detailed record

Full text