arXiv subjects

Jean Honorio

Publications and source records attributed to Jean Honorio.

At least 73 records · Page 4Linked to original sources

arXiv2020

Provable Sample Complexity Guarantees for Learning of Continuous-Action Graphical Games with Nonparametric Utilities

In this paper, we study the problem of learning the exact structure of continuous-action games with non-parametric utility functions. We propose an $\ell_1$ regularized method which encourages sparsity of the coefficients of the Fourier transform of the recovered utilities. Our method works by accessing very few Nash equilibria and their noisy utilities. Under certain technical conditions, our method also recovers the exact structure of these utility functions, and thus, the exact structure of the game. Furthermore, our method only needs a logarithmic number of samples in terms of the number of players and runs in polynomial time. We follow the primal-dual witness framework to provide provable theoretical guarantees.

cs.GT↗

arXiv2019

Provable Computational and Statistical Guarantees for Efficient Learning of Continuous-Action Graphical Games

In this paper, we study the problem of learning the set of pure strategy Nash equilibria and the exact structure of a continuous-action graphical game with quadratic payoffs by observing a small set of perturbed equilibria. A continuous-action graphical game can possibly have an uncountable set of Nash euqilibria. We propose a $\ell_{12}-$ block regularized method which recovers a graphical game, whose Nash equilibria are the $ε$-Nash equilibria of the game from which the data was generated (true game). Under a slightly stringent condition on the parameters of the true game, our method recovers the exact structure of the graphical game. Our method has a logarithmic sample complexity with respect to the number of players. It also runs in polynomial time.

cs.GT↗

arXiv2019

Computationally and statistically efficient learning of causal Bayes nets using path queries

Causal discovery from empirical data is a fundamental problem in many scientific domains. Observational data allows for identifiability only up to Markov equivalence class. In this paper we first propose a polynomial time algorithm for learning the exact correctly-oriented structure of the transitive reduction of any causal Bayesian network with high probability, by using interventional path queries. Each path query takes as input an origin node and a target node, and answers whether there is a directed path from the origin to the target. This is done by intervening on the origin node and observing samples from the target node. We theoretically show the logarithmic sample complexity for the size of interventional data per path query, for continuous and discrete networks. We then show how to learn the transitive edges using also logarithmic sample complexity (albeit in time exponential in the maximum number of parents for discrete networks), which allows us to learn the full network. We further extend our work by reducing the number of interventional path queries for learning rooted trees. We also provide an analysis of imperfect interventions.

cs.LG↗

arXiv2019

Cost-Aware Learning for Improved Identifiability with Multiple Experiments

We analyze the sample complexity of learning from multiple experiments where the experimenter has a total budget for obtaining samples. In this problem, the learner should choose a hypothesis that performs well with respect to multiple experiments, and their related data distributions. Each collected sample is associated with a cost which depends on the particular experiments. In our setup, a learner performs $m$ experiments, while incurring a total cost $C$. We first show that learning from multiple experiments allows to improve identifiability. Additionally, by using a Rademacher complexity approach, we show that the gap between the training and generalization error is $O(C^{-1/2})$. We also provide some examples for linear prediction, two-layer neural networks and kernel methods.

cs.LG↗

arXiv2019

Optimality Implies Kernel Sum Classifiers are Statistically Efficient

We propose a novel combination of optimization tools with learning theory bounds in order to analyze the sample complexity of optimal kernel sum classifiers. This contrasts the typical learning theoretic results which hold for all (potentially suboptimal) classifiers. Our work also justifies assumptions made in prior work on multiple kernel learning. As a byproduct of our analysis, we also provide a new form of Rademacher complexity for hypothesis classes containing only optimal classifiers.

cs.LG↗

arXiv2019

On the Correctness and Sample Complexity of Inverse Reinforcement Learning

Inverse reinforcement learning (IRL) is the problem of finding a reward function that generates a given optimal policy for a given Markov Decision Process. This paper looks at an algorithmic-independent geometric analysis of the IRL problem with finite states and actions. A L1-regularized Support Vector Machine formulation of the IRL problem motivated by the geometric analysis is then proposed with the basic objective of the inverse reinforcement problem in mind: to find a reward function that generates a specified optimal policy. The paper further analyzes the proposed formulation of inverse reinforcement learning with $n$ states and $k$ actions, and shows a sample complexity of $O(n^2 \log (nk))$ for recovering a reward function that generates a policy that satisfies Bellman's optimality condition with respect to the true transition probabilities.

cs.LG↗

arXiv2019

Minimax bounds for structured prediction

Structured prediction can be considered as a generalization of many standard supervised learning tasks, and is usually thought as a simultaneous prediction of multiple labels. One standard approach is to maximize a score function on the space of labels, which decomposes as a sum of unary and pairwise potentials, each depending on one or two specific labels, respectively. For this approach, several learning and inference algorithms have been proposed over the years, ranging from exact to approximate methods while balancing the computational complexity. However, in contrast to binary and multiclass classification, results on the necessary number of samples for achieving learning is still limited, even for a specific family of predictors such as factor graphs. In this work, we provide minimax bounds for a class of factor-graph inference models for structured prediction. That is, we characterize the necessary sample complexity for any conceivable algorithm to achieve learning of factor-graph predictors.

cs.LG↗

arXiv2019

Exact inference in structured prediction

Structured prediction can be thought of as a simultaneous prediction of multiple labels. This is often done by maximizing a score function on the space of labels, which decomposes as a sum of pairwise and unary potentials. The above is naturally modeled with a graph, where edges and vertices are related to pairwise and unary potentials, respectively. We consider the generative process proposed by Globerson et al. and apply it to general connected graphs. We analyze the structural conditions of the graph that allow for the exact recovery of the labels. Our results show that exact recovery is possible and achievable in polynomial time for a large class of graphs. In particular, we show that graphs that are bad expanders can be exactly recovered by adding small edge perturbations coming from the Erdős-Rényi model. Finally, as a byproduct of our analysis, we provide an extension of Cheeger's inequality.

cs.LG↗

arXiv2019

Learning Bayesian Networks with Low Rank Conditional Probability Tables

In this paper, we provide a method to learn the directed structure of a Bayesian network using data. The data is accessed by making conditional probability queries to a black-box model. We introduce a notion of simplicity of representation of conditional probability tables for the nodes in the Bayesian network, that we call "low rankness". We connect this notion to the Fourier transformation of real valued set functions and propose a method which learns the exact directed structure of a `low rank` Bayesian network using very few queries. We formally prove that our method correctly recovers the true directed structure, runs in polynomial time and only needs polynomial samples with respect to the number of nodes. We also provide further improvements in efficiency if we have access to some observational data.

cs.LG↗

arXiv2018

Information Theoretic Limits for Standard and One-Bit Compressed Sensing with Graph-Structured Sparsity

In this paper, we analyze the information theoretic lower bound on the necessary number of samples needed for recovering a sparse signal under different compressed sensing settings. We focus on the weighted graph model, a model-based framework proposed by Hegde et al. (2015), for standard compressed sensing as well as for one-bit compressed sensing. We study both the noisy and noiseless regimes. Our analysis is general in the sense that it applies to any algorithm used to recover the signal. We carefully construct restricted ensembles for different settings and then apply Fano's inequality to establish the lower bound on the necessary number of samples. Furthermore, we show that our bound is tight for one-bit compressed sensing, while for standard compressed sensing, our bound is tight up to a logarithmic factor of the number of non-zero entries in the signal.

cs.IT↗

arXiv2018

Learning discrete Bayesian networks in polynomial time and sample complexity

In this paper, we study the problem of structure learning for Bayesian networks in which nodes take discrete values. The problem is NP-hard in general but we show that under certain conditions we can recover the true structure of a Bayesian network with sufficient number of samples. We develop a mathematical model which does not assume any specific conditional probability distributions for the nodes. We use a primal-dual witness construction to prove that, under some technical conditions on the interaction between node pairs, we can do exact recovery of the parents and children of a node by performing group l_12-regularized multivariate regression. Thus, we recover the true Bayesian network structure. If degree of a node is bounded then the sample complexity of our proposed approach grows logarithmically with respect to the number of nodes in the Bayesian network. Furthermore, our method runs in polynomial time.

cs.LG↗

arXiv2018

Statistically and Computationally Efficient Variance Estimator for Kernel Ridge Regression

In this paper, we propose a random projection approach to estimate variance in kernel ridge regression. Our approach leads to a consistent estimator of the true variance, while being computationally more efficient. Our variance estimator is optimal for a large family of kernels, including cubic splines and Gaussian kernels. Simulation analysis is conducted to support our theory.

math.ST↗

arXiv2018

Learning latent variable structured prediction models with Gaussian perturbations

The standard margin-based structured prediction commonly uses a maximum loss over all possible structured outputs. The large-margin formulation including latent variables not only results in a non-convex formulation but also increases the search space by a factor of the size of the latent space. Recent work has proposed the use of the maximum loss over random structured outputs sampled independently from some proposal distribution, with theoretical guarantees. We extend this work by including latent variables. We study a new family of loss functions under Gaussian perturbations and analyze the effect of the latent space on the generalization bounds. We show that the non-convexity of learning with latent variables originates naturally, as it relates to a tight upper bound of the Gibbs decoder distortion with respect to the latent space. Finally, we provide a formulation using random samples that produces a tighter upper bound of the Gibbs decoder distortion up to a statistical accuracy, which enables a faster evaluation of the objective function. We illustrate the method with synthetic experiments and a computer vision application.

cs.LG↗

arXiv2018

Information-theoretic Limits for Community Detection in Network Models

We analyze the information-theoretic limits for the recovery of node labels in several network models. This includes the Stochastic Block Model, the Exponential Random Graph Model, the Latent Space Model, the Directed Preferential Attachment Model, and the Directed Small-world Model. For the Stochastic Block Model, the non-recoverability condition depends on the probabilities of having edges inside a community, and between different communities. For the Latent Space Model, the non-recoverability condition depends on the dimension of the latent space, and how far and spread are the communities in the latent space. For the Directed Preferential Attachment Model and the Directed Small-world Model, the non-recoverability condition depends on the ratio between homophily and neighborhood size. We also consider dynamic versions of the Stochastic Block Model and the Latent Space Model.

cs.LG↗

arXiv2018

Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time

MAP perturbation models have emerged as a powerful framework for inference in structured prediction. Such models provide a way to efficiently sample from the Gibbs distribution and facilitate predictions that are robust to random noise. In this paper, we propose a provably polynomial time randomized algorithm for learning the parameters of perturbed MAP predictors. Our approach is based on minimizing a novel Rademacher-based generalization bound on the expected loss of a perturbed MAP predictor, which can be computed in polynomial time. We obtain conditions under which our randomized learning algorithm can guarantee generalization to unseen examples.

cs.LG↗

arXiv2017

Learning Sparse Polymatrix Games in Polynomial Time and Sample Complexity

We consider the problem of learning sparse polymatrix games from observations of strategic interactions. We show that a polynomial time method based on $\ell_{1,2}$-group regularized logistic regression recovers a game, whose Nash equilibria are the $ε$-Nash equilibria of the game from which the data was generated (true game), in $\mathcal{O}(m^4 d^4 \log (pd))$ samples of strategy profiles --- where $m$ is the maximum number of pure strategies of a player, $p$ is the number of players, and $d$ is the maximum degree of the game graph. Under slightly more stringent separability conditions on the payoff matrices of the true game, we show that our method learns a game with the exact same Nash equilibria as the true game. We also show that $Ω(d \log (pm))$ samples are necessary for any method to consistently recover a game, with the same Nash-equilibria as the true game, from observations of strategic interactions. We verify our theoretical results through simulation experiments.

cs.LG↗

arXiv2017

Reconstructing a Bounded-Degree Directed Tree Using Path Queries

We present a randomized algorithm for reconstructing directed rooted trees of $n$ nodes and node degree at most $d$, by asking at most $O(dn\log^2 n)$ path queries. Each path query takes as input an origin node and a target node, and answers whether there is a directed path from the origin to the target. Regarding lower bounds, we show that any randomized algorithm requires at least $Ω(n\log n)$ queries, while any deterministic algorithm requires at least $Ω(dn)$ queries. Additionally, we present a $O(dn\log^3 n)$ randomized algorithm for noisy queries, and a $O(dn\log^2 n)$ randomized algorithm for additive queries on weighted trees.

cs.DS↗

arXiv2017

On the Statistical Efficiency of Compositional Nonparametric Prediction

In this paper, we propose a compositional nonparametric method in which a model is expressed as a labeled binary tree of $2k+1$ nodes, where each node is either a summation, a multiplication, or the application of one of the $q$ basis functions to one of the $p$ covariates. We show that in order to recover a labeled binary tree from a given dataset, the sufficient number of samples is $O(k\log(pq)+\log(k!))$, and the necessary number of samples is $Ω(k\log (pq)-\log(k!))$. We further propose a greedy algorithm for regression in order to validate our theoretical findings through synthetic experiments.

stat.ML↗