EV
Emmanouil-Vasileios Vlatakis-Gkaragkounis
cs.LGcs.GTmath.OCstat.MLcs.DScs.CCcs.MAmath.PRquant-phcs.AI
On Valency
published · living versionsW_2y3h6jgr·v1 · currentpublished
Where Should Learning Live? Regret Analysis for Text, Parameter, and Joint Adaptation
with Jungtaek Kim, Jaden Park, Jongwon Jeong, Kangwook Lee
1 version
W_qxwep63y·v1published
W_vr6myad9·v1published
Preprints & journals
32 papers in the corpus · 2018–2026Average-and Last-Iterate Lower Bounds for Optimistic Matrix Mirror-Prox in Quantum Zero-Sum Games2609.38835v1 · Yiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Pucheng Xiong2026 · 0 citationsarXiv
Prudent-Banker: No Extra Fees for Baseline Safety in Adversarial Bandits With and Without Delays2605.23351v1 · Ting Hu, Luanda Cai, Emmanouil-Vasileios Vlatakis-Gkaragkounis2026 · 0 citationsarXiv
Shuffling the Data, Stretching the Step-size: Sharper Bias in constant step-size SGD2604.10373v1 · Konstantinos Emmanouilidis, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Rene Vidal2026 · 0 citationsarXiv
No Coin Left Behind: Maximizing Strategic Surplus Against No-Regret Dynamics2604.05129v2 · Yiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis2026 · 0 citationsarXiv
Learning Safely Without Knowing the World:COMPASS-Hedge2603.22348v4 · Ting Hu, Luanda Cai, Emmanouil-Vasileios Vlatakis-Gkaragkounis2026 · 0 citationsarXiv
Sparks of Cooperative Reasoning: LLMs as Strategic Hanabi Agents2601.18077v3 · Mahesh Ramesh, Kaousheik Jayakumar, Aswinkumar Ramkumar et al.2026 · 0 citationsarXiv
Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics2512.00389v1 · Deep Patel, Emmanouil-Vasileios Vlatakis-Gkaragkounis2025 · 0 citationsarXiv
Armada: Memory-Efficient Distributed Training of Large-Scale Graph Neural Networks2502.17846v1 · Roger Waleffe, Devesh Sarda, Jason Mohoney et al.2025 · 0 citationsarXiv
Contracting with a Learning Agent2401.16198v1 · Guru Guruganesh, Yoav Kolumbus, Jon Schneider et al.2024 · 6 citationsarXiv
Exploiting hidden structures in non-convex games for convergence to Nash equilibrium2312.16609v1 · Iosif Sakos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Panayotis Mertikopoulos et al.2023 · 1 citationarXiv
A Quadratic Speedup in Finding Nash Equilibria of Quantum Zero-Sum Games2311.10859v2 · Francisca Vasconcelos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Panayotis Mertikopoulos et al.2023 · 0 citationsQuantum 9, 1737 (2025)
Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation2306.16617v2 · Yang Cai, Michael I. Jordan, Tianyi Lin et al.2023 · 0 citationsarXiv
Stochastic Methods in Variational Inequalities: Ergodicity, Bias and Refinements2306.16502v1 · Emmanouil-Vasileios Vlatakis-Gkaragkounis, Angeliki Giannou, Yudong Chen et al.2023 · 0 citationsarXiv
Chaos persists in large-scale multi-agent learning despite adaptive learning rates2306.01032v2 · Emmanouil-Vasileios Vlatakis-Gkaragkounis, Konstantinos Metaxas, Lampros Flokas et al.2023 · 0 citationsarXiv
Smoothed Complexity of SWAP in Local Graph Partitioning2305.15804v1 · Xi Chen, Chenghao Guo, Emmanouil-Vasileios Vlatakis-Gkaragkounis et al.2023 · 0 citationsarXiv
Algorithms and Complexity for Computing Nash Equilibria in Adversarial Team Games2301.02129v4 · Ioannis Anagnostides, Fivos Kalogiannis, Ioannis Panageas et al.2023 · 0 citationsarXiv
On the convergence of policy gradient methods to Nash equilibria in general stochastic games2210.08857v1 · Angeliki Giannou, Kyriakos Lotidis, Panayotis Mertikopoulos et al.2022 · 6 citationsarXiv
Efficiently Computing Nash Equilibria in Adversarial Team Markov Games2208.02204v1 · Fivos Kalogiannis, Ioannis Anagnostides, Ioannis Panageas et al.2022 · 4 citationsarXiv
The Computational Complexity of Multi-player Concave Games and Kakutani Fixed Points2207.07557v3 · Christos H. Papadimitriou, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Manolis Zampetakis2022 · 1 citationarXiv
First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces2206.02041v2 · Michael I. Jordan, Tianyi Lin, Emmanouil-Vasileios Vlatakis-Gkaragkounis2022 · 6 citationsarXiv
Near-Optimal Statistical Query Lower Bounds for Agnostically Learning Intersections of Halfspaces with Gaussian Marginals2202.05096v1 · Daniel Hsu, Clayton Sanford, Rocco Servedio et al.2022 · 2 citationsarXiv
Towards convergence to Nash equilibria in two-team zero-sum games2111.04178v4 · Fivos Kalogiannis, Ioannis Panageas, Emmanouil-Vasileios Vlatakis-Gkaragkounis2021 · 1 citationarXiv
On the Approximation Power of Two-Layer Networks of Random ReLUs2102.02336v2 · Daniel Hsu, Clayton Sanford, Rocco A. Servedio et al.2021 · 6 citationsProceedings of Thirty Fourth Conference on Learning Theory, PMLR 134 (2021) 2423-2461
Solving Min-Max Optimization with Hidden Structure via Gradient Descent Ascent2101.05248v1 · Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras2021 · 3 citationsarXiv
Survival of the strictest: Stable and unstable equilibria under regularized learning with partial information2101.04667v2 · Angeliki Giannou, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Panayotis Mertikopoulos2021 · 4 citationsarXiv
Optimal Private Median Estimation under Minimal Distributional Assumptions2011.06202v1 · Christos Tzamos, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Ilias Zadik2020 · 8 citationsarXiv
No-regret learning and mixed Nash equilibria: They do not mix2010.09514v2 · Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Thanasis Lianeas et al.2020 · 20 citationsarXiv
Reconstructing weighted voting schemes from partial information about their power indices2007.09599v2 · Huck Bennett, Anindya De, Rocco A. Servedio et al.2020 · 0 citationsarXiv
Smoothed complexity of local Max-Cut and binary Max-CSP1911.10381v1 · Xi Chen, Chenghao Guo, Emmanouil-Vasileios Vlatakis-Gkaragkounis et al.2019 · 8 citationsarXiv
Efficiently avoiding saddle points with zero order methods: No gradients required1910.13021v1 · Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras2019 · 13 citationsarXiv
Poincaré Recurrence, Cycles and Spurious Equilibria in Gradient-Descent-Ascent for Non-Convex Non-Concave Zero-Sum Games1910.13010v1 · Lampros Flokas, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Georgios Piliouras2019 · 4 citationsarXiv
Pattern Search Multidimensional Scaling1806.00416v3 · Georgios Paraskevopoulos, Efthymios Tzinis, Emmanouil-Vasileios Vlatakis-Gkaragkounis et al.2018 · 3 citationsarXiv
Career total: 39 works. 32 are in this corpus.
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.