no code implementations • 18 Mar 2024 • Alkis Kalavasis, Ilias Zadik, Manolis Zampetakis
We also provide a discrete analogue of our transfer inequality on the Boolean Hypercube $\{-1, 1\}^n$, and study its connections with the recent problem of Generalization on the Unseen of Abbe, Bengio, Lotfi and Rizk (ICML, 2023).
no code implementations • 21 Feb 2024 • Alkis Kalavasis, Amin Karbasi, Kasper Green Larsen, Grigoris Velegkas, Felix Zhou
Departing from the requirement of polynomial time algorithms, using the DP-to-Replicability reduction of Bun, Gaboardi, Hopkins, Impagliazzo, Lei, Pitassi, Sorrell, and Sivakumar [STOC, 2023], we show how to obtain a replicable algorithm for large-margin halfspaces with improved sample complexity with respect to the margin parameter $\tau$, but running time doubly exponential in $1/\tau^2$ and worse sample complexity dependence on $\epsilon$ than one of our previous algorithms.
no code implementations • 6 Nov 2023 • Andreas Galanis, Alkis Kalavasis, Anthimos Vardis Kandiros
For general $H$-colorings, we show that standard conditions that guarantee sampling, such as Dobrushin's condition, are insufficient for one-sample learning; on the positive side, we provide a general condition that is sufficient to guarantee linear-time learning and obtain applications for proper colorings and permissive models.
no code implementations • 8 Oct 2023 • Constantine Caramanis, Dimitris Fotakis, Alkis Kalavasis, Vasilis Kontonis, Christos Tzamos
Deep Neural Networks and Reinforcement Learning methods have empirically shown great promise in tackling challenging combinatorial problems.
no code implementations • 23 May 2023 • Alkis Kalavasis, Amin Karbasi, Shay Moran, Grigoris Velegkas
When two different parties use the same learning rule on their own data, how can we test whether the distributions of the two outcomes are similar?
no code implementations • 23 Nov 2022 • Dimitris Fotakis, Alkis Kalavasis, Christos Tzamos
We design a Markov chain whose stationary distribution coincides with $\mathcal{D}$ and give an algorithm to obtain exact samples using the technique of Coupling from the Past.
no code implementations • 24 Oct 2022 • Alkis Kalavasis, Konstantinos Stavropoulos, Manolis Zampetakis
In this work, we address two questions: (i) Are there general families of SIIRVs with unbounded support that can be learned with sample complexity independent of both $n$ and the maximal element of the support?
no code implementations • 5 Oct 2022 • Alkis Kalavasis, Grigoris Velegkas, Amin Karbasi
Second, we consider the problem of multiclass classification with structured data (such as data lying on a low dimensional manifold or satisfying margin conditions), a setting which is captured by partial concept classes (Alon, Hanneke, Holzman and Moran, FOCS '21).
no code implementations • 4 Oct 2022 • Hossein Esfandiari, Alkis Kalavasis, Amin Karbasi, Andreas Krause, Vahab Mirrokni, Grigoris Velegkas
Similarly, for stochastic linear bandits (with finitely and infinitely many arms) we develop replicable policies that achieve the best-known problem-independent regret bounds with an optimal dependency on the replicability parameter.
no code implementations • 19 Feb 2022 • Jason Milionis, Alkis Kalavasis, Dimitris Fotakis, Stratis Ioannidis
We provide computationally efficient, differentially private algorithms for the classical regression settings of Least Squares Fitting, Binary Regression and Linear Regression with unbounded covariates.
no code implementations • 4 Nov 2021 • Dimitris Fotakis, Alkis Kalavasis, Eleni Psaroudaki
We introduce a generative model for Label Ranking, in noiseless and noisy nonparametric regression settings, and provide sample complexity bounds for learning algorithms in both cases.
no code implementations • 22 Aug 2021 • Dimitris Fotakis, Alkis Kalavasis, Vasilis Kontonis, Christos Tzamos
Our main algorithmic result is that essentially any problem learnable from fine grained labels can also be learned efficiently when the coarse data are sufficiently informative.
no code implementations • 2 Nov 2020 • Dimitris Fotakis, Alkis Kalavasis, Konstantinos Stavropoulos
We consider the problem of learning the true ordering of a set of alternatives from largely incomplete and noisy rankings.
no code implementations • 5 Jul 2020 • Dimitris Fotakis, Alkis Kalavasis, Christos Tzamos
A stunning consequence is that virtually any statistical task (e. g., learning in total variation distance, parameter estimation, uniformity or identity testing) that can be performed efficiently for Boolean product distributions, can also be performed from truncated samples, with a small increase in sample complexity.