Ioannis Panageas
Ioannis Panageas
Assistant Professor, Department of Computer Science, University of California, Irvine
Bestätigte E-Mail-Adresse bei ics.uci.edu - Startseite
Titel
Zitiert von
Zitiert von
Jahr
First-order methods almost always avoid strict saddle points
JD Lee, I Panageas, G Piliouras, M Simchowitz, MI Jordan, B Recht
Mathematical programming 176 (1-2), 311-337, 2019
155*2019
Gradient descent only converges to minimizers: Non-isolated critical points and invariant regions
I Panageas, G Piliouras
Proceedings of the Conference on Innovations in Theoretical Computer Science, 2017
118*2017
The limit points of (optimistic) gradient descent in min-max optimization
C Daskalakis, I Panageas
Advances in Neural Information Processing Systems 31, 9236-9246, 2018
912018
Multiplicative Weights Update with Constant Step-Size in Congestion Games: Convergence, Limit Cycles and Chaos
G Palaiopanos, I Panageas, G Piliouras
31st Annual Conference on Neural Information Processing Systems, 2017
632017
Natural selection as an inhibitor of genetic diversity: Multiplicative weights updates algorithm and a conjecture of haploid genetics [working paper abstract]
R Mehta, I Panageas, G Piliouras
Proceedings of the 2015 Conference on Innovations in Theoretical Computer …, 2015
49*2015
Last-iterate convergence: Zero-sum games and constrained min-max optimization
C Daskalakis, I Panageas
Proceedings of the Conference on Innovations in Theoretical Computer Science, 2019
432019
Average case performance of replicator dynamics in potential games via computing regions of attraction
I Panageas, G Piliouras
Proceedings of the 2016 ACM Conference on Economics and Computation, 703-720, 2016
33*2016
Mutation, sexual reproduction and survival in dynamic environments
R Mehta, I Panageas, G Piliouras, P Tetali, VV Vazirani
Proceedings of the 2017 Conference on Innovations in Theoretical Computer …, 2015
15*2015
Regression from dependent observations
C Daskalakis, N Dikkala, I Panageas
Proceedings of the 51st Annual ACM symposium on Theory of Computing, 2019
132019
Cycles in zero-sum differential games and biological diversity
T Mai, M Mihail, I Panageas, W Ratcliff, V Vazirani, P Yunker
Proceedings of the 2018 ACM Conference on Economics and Computation, 339-350, 2018
12*2018
The computational complexity of genetic diversity
R Mehta, I Panageas, G Piliouras, S Yazdanbod
24th Annual European Symposium on Algorithms (ESA 2016), 2016
12*2016
First-order methods almost always avoid saddle points: The case of vanishing step-sizes
I Panageas, G Piliouras, X Wang
Advances in Neural Information Processing Systems, 6474-6483, 2019
102019
Support-theoretic subgraph preconditioners for large-scale SLAM
YD Jian, D Balcan, I Panageas, P Tetali, F Dellaert
2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 9-16, 2013
102013
Evolutionary dynamics in finite populations mix rapidly
I Panageas, P Srivastava, NK Vishnoi
Proceedings of the twenty-seventh annual ACM-SIAM symposium on Discrete …, 2016
82016
Opinion dynamics in networks: Convergence, stability and lack of explosion
T Mai, I Panageas, VV Vazirani
Proceedings of the 44th International Colloquium on Automata, Languages, and …, 2016
72016
Last iterate convergence in no-regret learning: constrained min-max optimization for convex-concave landscapes
Q Lei, SG Nagarajan, I Panageas, X Wang
arXiv preprint arXiv:2002.06768, 2020
62020
Depth-Width Trade-offs for ReLU Networks via Sharkovsky's Theorem
V Chatziafratis, SG Nagarajan, I Panageas, X Wang
arXiv preprint arXiv:1912.04378, 2019
62019
Mixing time of Markov chains, dynamical systems and evolution
I Panageas, NK Vishnoi
43rd International Colloquium on Automata, Languages, and Programming (ICALP …, 2016
62016
Logistic-Regression with peer-group effects via inference in higher order Ising models
C Daskalakis, N Dikkala, I Panageas
arXiv preprint arXiv:2003.08259, 2020
52020
On the Analysis of EM for truncated mixtures of two Gaussians
SG Nagarajan, I Panageas
Algorithmic Learning Theory, 634-659, 2020
4*2020
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20