Search Results for author: Dimitris Fotakis

Found 14 papers, 2 papers with code

Perfect Sampling from Pairwise Comparisons

no code implementations23 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.

Differentially Private Regression with Unbounded Covariates

no code implementations19 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.


Identity testing for Mallows model

no code implementations NeurIPS 2021 Róbert Busa-Fekete, Dimitris Fotakis, Balazs Szorenyi, Emmanouil Zampetakis

In this paper, we devise identity tests for ranking data that is generated from Mallows model both in the \emph{asymptotic} and \emph{non-asymptotic} settings.

Private and Non-private Uniformity Testing for Ranking Data

no code implementations NeurIPS 2021 Róbert Busa-Fekete, Dimitris Fotakis, Emmanouil Zampetakis

We study the problem of uniformity testing for statistical data that consists of rankings over $m$ items where the alternative class is restricted to Mallows models with single parameter.

Label Ranking through Nonparametric Regression

no code implementations4 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.


Efficient Algorithms for Learning from Coarse Labels

no code implementations22 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.

Learning Augmented Online Facility Location

1 code implementation17 Jul 2021 Dimitris Fotakis, Evangelia Gergatsouli, Themis Gouleakis, Nikolas Patris

We prove that the competitive ratio decreases smoothly from sublogarithmic in the number of demands to constant, as the error, i. e., the total distance of the predicted locations to the optimal facility locations, decreases towards zero.

Solving Inverse Problems for Spectral Energy Distributions with Deep Generative Networks

no code implementations9 Dec 2020 Agapi Rissaki, Orestis Pavlou, Dimitris Fotakis, Vicky Papadopoulou, Andreas Efstathiou

We propose an end-to-end approach for solving inverse problems for a class of complex astronomical signals, namely Spectral Energy Distributions (SEDs).

Efficient Online Learning of Optimal Rankings: Dimensionality Reduction via Gradient Descent

1 code implementation NeurIPS 2020 Dimitris Fotakis, Thanasis Lianeas, Georgios Piliouras, Stratis Skoulakis

We consider a natural model of online preference aggregation, where sets of preferred items $R_1, R_2, \ldots, R_t$ along with a demand for $k_t$ items in each $R_t$, appear online.

Dimensionality Reduction online learning

Aggregating Incomplete and Noisy Rankings

no code implementations2 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.

Efficient Parameter Estimation of Truncated Boolean Product Distributions

no code implementations5 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.

Optimal Learning of Mallows Block Model

no code implementations3 Jun 2019 Róbert Busa-Fekete, Dimitris Fotakis, Balázs Szörényi, Manolis Zampetakis

The main result of the paper is a tight sample complexity bound for learning Mallows and Generalized Mallows Model.

Learning Powers of Poisson Binomial Distributions

no code implementations18 Jul 2017 Dimitris Fotakis, Vasilis Kontonis, Piotr Krysta, Paul Spirakis

The $k$'th power of this distribution, for $k$ in a range $[m]$, is the distribution of $P_k = \sum_{i=1}^n X_i^{(k)}$, where each Bernoulli random variable $X_i^{(k)}$ has $\mathbb{E}[X_i^{(k)}] = (p_i)^k$.

Cannot find the paper you are looking for? You can Submit a new open access paper.