IM
Ioannis Mitliagkas
cs.LGstat.MLcs.AImath.OCcs.CVcs.GTcs.DCcs.ITmath.ITstat.ME
On Valency
published · living versionsW_u7fa5rax·v1 · currentpublished
MLSys: The New Frontier of Machine Learning Systems
with Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen +64
1 version
Preprints & journals
68 papers in the corpus · 2011–2026Generalization Measures under Controlled Covariate Shift: A Regime-Aware Benchmark2602.01718v2 · Sora Nakai, Youssef Fadhloun, Kacem Mathlouthi et al.2026 · 0 citationsarXiv
Adaptive Batch Sizes Using Non-Euclidean Gradient Noise Scales for Stochastic Sign and Spectral Descent2602.03001v2 · Hiroki Naganuma, Shagun Gupta, Youssef Briki et al.2026 · 0 citationsarXiv
Accelerated Stochastic Power Iteration1707.02670v1 · Christopher De Sa, Bryan He, Ioannis Mitliagkas et al.2017 · 20 citationsarXiv
Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data2605.11170v2 · Ahmed Mehdi Inane, Vincent Quirion, Gintare Karolina Dziugaite et al.2026 · 0 citationsarXiv
A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond2510.19382v2 · Nikos Tsikouras, Yorgos Pantis, Ioannis Mitliagkas et al.2025 · 0 citationsarXiv
Orth-Dion: Eliminating Geometric Mismatch in Distributed Low-Rank Spectral Optimization2605.16341v1 · Tatsuhiro Nakamori, Laura Gomezjurado Gonzalez, Ganesh Talluri et al.2026 · 0 citationsarXiv
Navigating Potholes with Geometry-Aware Sharpness Minimization2605.16134v1 · Simon Dufort-Labb'e, Mehrab Hamidi, Razvan Pascanu et al.2026 · 0 citationsarXiv
Understanding Adam Requires Better Rotation Dependent Assumptions2410.19964v3 · Tianyue H. Zhang, Lucas Maes, Alan Milligan et al.2024 · 0 citationsarXiv
Pseudo-Asynchronous Local SGD: Robust and Efficient Data-Parallel Training2504.18454v2 · Hiroki Naganuma, Xinzhi Zhang, Man-Chung Yue et al.2025 · 0 citationsarXiv
Compositional Risk Minimization2410.06303v3 · Divyat Mahajan, Mohammad Pezeshki, Charles Arnal et al.2024 · 0 citationsarXiv
Generating Tabular Data Using Heterogeneous Sequential Feature Forest Flow Matching2410.15516v1 · Ange-Cl'ement Akazan, Alexia Jolicoeur-Martineau, Ioannis Mitliagkas2024 · 0 citationsarXiv
Solving Hidden Monotone Variational Inequalities with Surrogate Losses2411.05228v3 · Ryan D'Orazio, Danilo Vucetic, Zichu Liu et al.2024 · 0 citationsarXiv
Learning to Defer for Causal Discovery with Imperfect Experts2502.13132v1 · Oscar Clivio, Divyat Mahajan, Perouz Taslakian et al.2025 · 0 citationsarXiv
Performative Prediction with Neural Networks2304.06879v3 · Mehrnaz Mofakhami, Ioannis Mitliagkas, Gauthier Gidel2023 · 1 citationarXiv
Performance Control in Early Exiting to Deploy Large Models at the Same Cost of Smaller Ones2412.19325v1 · Mehrnaz Mofakhami, Reza Bayat, Ioannis Mitliagkas et al.2024 · 0 citationsarXiv
Towards efficient representation identification in supervised learning2204.04606v2 · Kartik Ahuja, Divyat Mahajan, Vasilis Syrgkanis et al.2022 · 1 citationarXiv
CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning2210.01742v4 · Charles Guille-Escuret, Pau Rodriguez, David Vazquez et al.2022 · 2 citationsAdvances in Neural Information Processing Systems 36 (2024)
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection2308.11480v2 · Charles Guille-Escuret, Pierre-Andr'e Noel, Ioannis Mitliagkas et al.2023 · 1 citationarXiv
Feature learning as alignment: a structural property of gradient descent in non-linear neural networks2402.05271v4 · Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala2024 · 0 citationsarXiv
Generalizing to unseen domains via distribution matching1911.00804v6 · Isabela Albuquerque, Joao Monteiro, Mohammad Darvishi et al.2019 · 86 citationsarXiv
Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition2406.09073v1 · Eleni Triantafillou, Peter Kairouz, Fabian Pedregosa et al.2024 · 1 citationarXiv
A Study of Condition Numbers for First-Order Optimization2012.05782v2 · Charles Guille-Escuret, Baptiste Goujaud, Manuela Girotti et al.2020 · 2 citationsInternational Conference on Artificial Intelligence and Statistics. PMLR, 2021. p. 1261-1269
Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound2203.00342v3 · Charles Guille-Escuret, Adam Ibrahim, Baptiste Goujaud et al.2022 · 2 citationsAdvances in Neural Information Processing Systems 35 (2022): 24893-24904
Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation2211.01939v3 · Divyat Mahajan, Ioannis Mitliagkas, Brady Neal et al.2022 · 0 citationsarXiv
Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation2307.02598v2 · S'ebastien Lachapelle, Divyat Mahajan, Ioannis Mitliagkas et al.2023 · 1 citationarXiv
Accelerated Stochastic Power Iteration.31187095 · De Sa, Christopher, He, Bryan, Mitliagkas, Ioannis et al.2023 · 20 citationsProceedings of machine learning research. 2018;84:58-67
Towards Out-of-Distribution Adversarial Robustness2210.03150v4 · Adam Ibrahim, Charles Guille-Escuret, Ioannis Mitliagkas et al.2022 · 0 citationsarXiv
LEAD: Min-Max Optimization from a Physical Perspective2010.13846v4 · Reyhane Askari Hemmat, Amartya Mitra, Guillaume Lajoie et al.2020 · 0 citationsarXiv
No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths2306.11922v1 · Charles Guille-Escuret, Hiroki Naganuma, Kilian Fatras et al.2023 · 0 citationsarXiv
Synergies between Disentanglement and Sparsity: Generalization and Identifiability in Multi-Task Learning2211.14666v2 · S'ebastien Lachapelle, Tristan Deleu, Divyat Mahajan et al.2022 · 1 citationarXiv
Empirical Study on Optimizer Selection for Out-of-Distribution Generalization2211.08583v3 · Hiroki Naganuma, Kartik Ahuja, Shiro Takagi et al.2022 · 3 citationsarXiv
A Modern Take on the Bias-Variance Tradeoff in Neural Networks1810.08591v4 · Brady Neal, Sarthak Mittal, Aristide Baratin et al.2018 · 67 citationsICML 2019 Workshop on Identifying and Understanding Deep Learning Phenomena
Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize2110.15412v3 · Ryan D'Orazio, Nicolas Loizou, Issam Laradji et al.2021 · 11 citationsarXiv
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games2206.05825v4 · Samuel Sokota, Ryan D'Orazio, J. Zico Kolter et al.2022 · 6 citationsarXiv
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD2209.14863v2 · Alireza Mousavi-Hosseini, Sejun Park, Manuela Girotti et al.2022 · 6 citationsarXiv
Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization2106.06607v2 · Kartik Ahuja, Ethan Caballero, Dinghuai Zhang et al.2021 · 83 citationsarXiv
A Reproducible and Realistic Evaluation of Partial Domain Adaptation Methods2210.01210v1 · Tiago Salvador, Kilian Fatras, Ioannis Mitliagkas et al.2022 · 1 citationarXiv
Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation2206.11180v1 · Kilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas2022 · 3 citationsarXiv
Stochastic Gradient Descent-Ascent and Consensus Optimization for Smooth Games: Convergence Analysis under Expected Co-coercivity2107.00052v2 · Nicolas Loizou, Hugo Berard, Gauthier Gidel et al.2021 · 5 citationsarXiv
Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks2110.10815v1 · Manuela Girotti, Ioannis Mitliagkas, Gauthier Gidel2021 · 0 citationsarXiv
Gotta Go Fast When Generating Data with Score-Based Models2105.14080v1 · Alexia Jolicoeur-Martineau, Ke Li, R'emi Pich'e-Taillefer et al.2021 · 19 citationsarXiv
In Search of Robust Measures of Generalization2010.11924v2 · Gintare Karolina Dziugaite, Alexandre Drouin, Brady Neal et al.2020 · 4 citationsarXiv
Gradient penalty from a maximum margin perspective1910.06922v2 · Alexia Jolicoeur-Martineau, Ioannis Mitliagkas2019 · 2 citationsarXiv
Adversarial score matching and improved sampling for image generation2009.05475v2 · Alexia Jolicoeur-Martineau, R'emi Pich'e-Taillefer, R'emi Tachet des Combes et al.2020 · 29 citationsarXiv
Linear Lower Bounds and Conditioning of Differentiable Games1906.07300v3 · Adam Ibrahim, Waiss Azizian, Gauthier Gidel et al.2019 · 26 citationsProceedings of the 37 th International Conference on Machine Learning, Vienna, Austria, PMLR 119, 2020
Negative Momentum for Improved Game Dynamics1807.04740v5 · Gauthier Gidel, Reyhane Askari Hemmat, Mohammad Pezeshki et al.2018 · 16 citationsarXiv
Stochastic Hamiltonian Gradient Methods for Smooth Games2007.04202v1 · Nicolas Loizou, Hugo Berard, Alexia Jolicoeur-Martineau et al.2020 · 14 citationsarXiv
A Tight and Unified Analysis of Gradient-Based Methods for a Whole Spectrum of Games1906.05945v5 · Waiss Azizian, Ioannis Mitliagkas, Simon Lacoste-Julien et al.2019 · 4 citationsarXiv
Accelerating Smooth Games by Manipulating Spectral Shapes2001.00602v2 · Waiss Azizian, Damien Scieur, Ioannis Mitliagkas et al.2020 · 21 citationsarXiv
MLSys: The New Frontier of Machine Learning Systems1904.03257v3 · Alexander Ratner, Dan Alistarh, Gustavo Alonso et al.2019 · 20 citationsarXivon Valency
Career total: 97 works. 68 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.