Ioannis (Yannis) Mitliagkas
Université de Montréal
H-index: 30
North America-Canada
Top articles of Ioannis (Yannis) Mitliagkas
Title | Journal | Author(s) | Publication Date |
|---|---|---|---|
Gradient descent induces alignment between weights and the empirical NTK for deep non-linear networks | arXiv preprint arXiv:2402.05271 | Daniel Beaglehole Ioannis Mitliagkas Atish Agarwala | 2024/2/7 |
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning | Advances in Neural Information Processing Systems | Charles Guille-Escuret Pau Rodriguez David Vazquez Ioannis Mitliagkas Joao Monteiro | 2024/2/13 |
Additive decoders for latent variables identification and cartesian-product extrapolation | Advances in Neural Information Processing Systems | Sébastien Lachapelle Divyat Mahajan Ioannis Mitliagkas Simon Lacoste-Julien | 2024/2/13 |
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection | arXiv preprint arXiv:2308.11480 | Charles Guille-Escuret Pierre-André Noël Ioannis Mitliagkas David Vazquez Joao Monteiro | 2023/8/22 |
Synergies between disentanglement and sparsity: Generalization and identifiability in multi-task learning | Sébastien Lachapelle Tristan Deleu Divyat Mahajan Ioannis Mitliagkas Yoshua Bengio | 2023/7/3 | |
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths | arXiv preprint arXiv:2306.11922 | Charles Guille-Escuret Hiroki Naganuma Kilian Fatras Ioannis Mitliagkas | 2023/6/20 |
Performative prediction with neural networks | Mehrnaz Mofakhami Ioannis Mitliagkas Gauthier Gidel | 2023/4/11 | |
Gradient descent is optimal under lower restricted secant inequality and upper error bound | Advances in Neural Information Processing Systems | Charles Guille-Escuret Adam Ibrahim Baptiste Goujaud Ioannis Mitliagkas | 2022/12/6 |
A reproducible and realistic evaluation of partial domain adaptation methods | arXiv preprint arXiv:2210.01210 | Tiago Salvador Kilian Fatras Ioannis Mitliagkas Adam Oberman | 2022/10/3 |
Neural networks efficiently learn low-dimensional representations with sgd | arXiv preprint arXiv:2209.14863 | Alireza Mousavi-Hosseini Sejun Park Manuela Girotti Ioannis Mitliagkas Murat A Erdogdu | 2022/9/29 |
Optimal transport meets noisy label robust loss and mixup regularization for domain adaptation | Kilian Fatras Hiroki Naganuma Ioannis Mitliagkas | 2022/11/28 | |
Towards efficient representation identification in supervised learning | Kartik Ahuja Divyat Mahajan Vasilis Syrgkanis Ioannis Mitliagkas | 2022/6/28 | |
Empirical study on optimizer selection for out-of-distribution generalization | arXiv preprint arXiv:2211.08583 | Hiroki Naganuma Kartik Ahuja Shiro Takagi Tetsuya Motokawa Rio Yokota | 2022/11/15 |
A unified approach to reinforcement learning, quantal response equilibria, and two-player zero-sum games | arXiv preprint arXiv:2206.05825 | Samuel Sokota Ryan D'Orazio J Zico Kolter Nicolas Loizou Marc Lanctot | 2022/6/12 |
Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation | arXiv preprint arXiv:2211.01939 | Divyat Mahajan Ioannis Mitliagkas Brady Neal Vasilis Syrgkanis | 2022/11/3 |
Towards out-of-distribution adversarial robustness | arXiv preprint arXiv:2210.03150 | Adam Ibrahim Charles Guille-Escuret Ioannis Mitliagkas Irina Rish David Krueger | 2022/10/6 |
On stochastic mirror descent: Convergence analysis and adaptive variants | Beyond First-Order Methods in ML Systems Workshop, Int. Conf. Machine Learning | Ryan D’Orazio Nicolas Loizou Issam Laradji Ioannis Mitliagkas | 2021 |
Invariance principle meets information bottleneck for out-of-distribution generalization | Advances in Neural Information Processing Systems | Kartik Ahuja Ethan Caballero Dinghuai Zhang Jean-Christophe Gagnon-Audet Yoshua Bengio | 2021/12/6 |
Stochastic mirror descent: Convergence analysis and adaptive variants via the mirror stochastic polyak stepsize | arXiv preprint arXiv:2110.15412 | Ryan D'Orazio Nicolas Loizou Issam Laradji Ioannis Mitliagkas | 2021/10/28 |
Convergence analysis and implicit regularization of feedback alignment for deep linear networks | arXiv preprint arXiv:2110.10815 | Manuela Girotti Ioannis Mitliagkas Gauthier Gidel | 2021/10/20 |
Co-Authors
