| On the almost sure convergence of stochastic gradient descent in non-convex problems P Mertikopoulos, N Hallak, A Kavis, V Cevher Advances in Neural Information Processing Systems 33, 1117-1128, 2020 | 154 | 2020 |
| Mirrored Langevin Dynamics YP Hsieh, A Kavis, P Rolland, V Cevher Advances in Neural Information Processing Systems, 2883-2892, 2018 | 128 | 2018 |
| UniXGrad: A Universal, Adaptive Algorithm with Optimal Guarantees for Constrained Optimization A Kavis, K Levy, F Bach, V Cevher Conference on Neural Information Processing Systems (NeurIPS) 2019, 2019 | 87 | 2019 |
| Storm+: Fully adaptive sgd with recursive momentum for nonconvex optimization K Levy, A Kavis, V Cevher Advances in Neural Information Processing Systems 34, 20571-20582, 2021 | 65* | 2021 |
| High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize A Kavis, KY Levy, V Cevher International Conference on Learning Representations (ICLR) 2022, 2022 | 60 | 2022 |
| Adaptive stochastic variance reduction for non-convex finite-sum minimization A Kavis, S Skoulakis, K Antonakopoulos, LT Dadi, V Cevher Advances in Neural Information Processing Systems 35, 23524-23538, 2022 | 22 | 2022 |
| Extra-newton: A first approach to noise-adaptive accelerated second-order methods K Antonakopoulos, A Kavis, V Cevher Advances in Neural Information Processing Systems 35, 29859-29872, 2022 | 17 | 2022 |
| Sifting through the noise: Universal first-order methods for stochastic variational inequalities K Antonakopoulos, T Pethick, A Kavis, P Mertikopoulos, V Cevher Advances in Neural Information Processing Systems 34, 13099-13111, 2021 | 13 | 2021 |
| Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness A Agafonov, D Kamzolov, A Gasnikov, A Kavis, K Antonakopoulos, ... arXiv preprint arXiv:2309.01570v2, 2023 | 10 | 2023 |
| Adaptive and optimal second-order optimistic methods for minimax optimization R Jiang, A Kavis, Q Jin, S Sanghavi, A Mokhtari Advances in Neural Information Processing Systems 37, 94130-94162, 2024 | 9 | 2024 |
| Alternation makes the adversary weaker in two-player games V Cevher, A Cutkosky, A Kavis, G Piliouras, S Skoulakis, L Viano Advances in Neural Information Processing Systems 36, 18263-18290, 2023 | 8 | 2023 |
| Upweighting easy samples in fine-tuning mitigates forgetting S Sanyal, H Prairie, R Das, A Kavis, S Sanghavi arXiv preprint arXiv:2502.02797, 2025 | 5 | 2025 |
| Double-loop unadjusted langevin algorithm P Rolland, A Eftekhari, A Kavis, V Cevher International Conference on Machine Learning, 8169-8177, 2020 | 5 | 2020 |
| Efficient learning of smooth probability functions from Bernoulli tests with guarantees P Rolland, A Kavis, A Immer, A Singla, V Cevher International Conference on Machine Learning, 5459-5467, 2019 | 4 | 2019 |
| Understanding Self-Supervised Learning via Gaussian Mixture Models P Bansal, A Kavis, S Sanghavi arXiv preprint arXiv:2411.03517, 2024 | 3* | 2024 |
| Online Learning-guided Learning Rate Adaptation via Gradient Alignment R Jiang, A Kavis, A Mokhtari arXiv preprint arXiv:2506.08419, 2025 | 1 | 2025 |
| Universal Gradient Methods for Stochastic Convex Optimization A Rodomanov, A Kavis, Y Wu, K Antonakopoulos, V Cevher International Conference on Machine Learning 41, 42620-42646, 2024 | | 2024 |
| Supplementary Materials for Mirrored Langevin Dynamics YP Hsieh, A Kavis, P Rolland, V Cevher | | |
Volkan CevherAssociate Professor, LIONS, EPFL. Amazon Scholar (AGI Foundations).Verified email at epfl.ch
