Search Results for author:
Found 74 papers, 3 papers with code
Personalized Federated X -armed Bandit
In this work, we study the personalized federated $\mathcal{X}$-armed bandit problem, where the heterogeneous local objectives of the clients are optimized simultaneously in the federated learning paradigm.
Invex Programs: First Order Algorithms and Their Convergence
Invex programs are a special kind of non-convex problems which attain global minima at every stationary point.
Outlier-robust Estimation of a Sparse Linear Model Using Invexity
In this paper, we study problem of estimating a sparse regression vector with correct support in the presence of outlier samples.
Partial Inference in Structured Prediction
In this paper, we examine the problem of partial inference in the context of structured prediction.
Matrix Completion from General Deterministic Sampling Patterns
Most of the existing works on provable guarantees for low-rank matrix completion algorithms rely on some unrealistic assumptions such that matrix entries are sampled randomly or the sampling pattern has a specific structure.
PyXAB -- A Python Library for $\mathcal{X}$-Armed Bandit and Online Blackbox Optimization Algorithms
We introduce a Python open-source library for $\mathcal{X}$-armed bandit and online blackbox optimization named PyXAB.
Exact Inference in High-order Structured Prediction
In this paper, we study the problem of inference in high-order structured prediction tasks.
Support Recovery in Sparse PCA with Non-Random Missing Data
We analyze a practical algorithm for sparse PCA on incomplete and noisy data under a general non-random sampling scheme.
Learning Against Distributional Uncertainty: On the Trade-off Between Robustness and Specificity
Trustworthy machine learning aims at combating distributional uncertainties in training data distributions compared to population distributions.
MEDIC: Remove Model Backdoors via Importance Driven Cloning
It trains the clone model from scratch on a very small subset of samples and aims to minimize a cloning loss that denotes the differences between the activations of important neurons across the two models.
A Theoretical Study of The Effects of Adversarial Attacks on Sparse Regression
This paper analyzes $\ell_1$ regularized linear regression under the challenging scenario of having only adversarially corrupted data for training.
Meta Learning for High-dimensional Ising Model Selection Using $\ell_1$-regularized Logistic Regression
In this paper, we consider the meta learning problem for estimating the graphs associated with high-dimensional Ising models, using the method of $\ell_1$-regularized logistic regression for neighborhood selection of each node.
A Novel Plug-and-Play Approach for Adversarially Robust Generalization
In this work, we propose a robust framework that employs adversarially robust training to safeguard the machine learning models against perturbed testing data.
Meta Sparse Principal Component Analysis
We assume each task to be a different random Principal Component (PC) matrix with a possibly different support and that the support union of the PC matrices is small.
Provable Guarantees for Sparsity Recovery with Deterministic Missing Data Patterns
We study the problem of consistently recovering the sparsity pattern of a regression parameter vector from correlated observations governed by deterministic missing data patterns using Lasso.
Sparse Mixed Linear Regression with Guarantees: Taming an Intractable Problem with Invex Relaxation
Since the data is unlabeled, our task is not only to figure out a good approximation of the regression parameter vectors but also to label the dataset correctly.
Federated X-Armed Bandit
This work establishes the first framework of federated $\mathcal{X}$-armed bandit, where different clients face heterogeneous local objective functions defined on the same domain and are required to collaboratively figure out the global optimum.
Support Recovery in Sparse PCA with Incomplete Data
We study a practical algorithm for sparse principal component analysis (PCA) of incomplete and noisy data.
Dual Convexified Convolutional Neural Networks
To overcome this, we propose a highly novel weight recovery algorithm, which takes the dual solution and the kernel information as the input, and recovers the linear weight and the output of convolutional layer, instead of weight parameter.
Federated Myopic Community Detection with One-shot Communication
We provide an efficient algorithm, which computes a consensus signed weighted graph from clients evidence, and recovers the underlying network structure in the central server.
A Lower Bound for the Sample Complexity of Inverse Reinforcement Learning
Inverse reinforcement learning (IRL) is the task of finding a reward function that generates a desired optimal policy for a given Markov Decision Process (MDP).
Information-Theoretic Bounds for Integral Estimation
For functions with nonzero fourth derivatives, the Gaussian Quadrature method achieves an upper bound which is not tight with the information-theoretic lower bound.
Fair Sparse Regression with Clustering: An Invex Relaxation for a Combinatorial Problem
To the best of our knowledge, this is the first invex relaxation for a combinatorial problem.
A Simple Unified Framework for High Dimensional Bandit Problems
Stochastic high dimensional bandit problems with low dimensional structures are useful in different applications such as online advertising and drug discovery.
On the Fundamental Limits of Exact Inference in Structured Prediction
Inference is a main task in structured prediction and it is naturally modeled with a graph.
Inverse Reinforcement Learning in a Continuous State Space with Formal Guarantees
Inverse Reinforcement Learning (IRL) is the problem of finding a reward function which describes observed/known expert behavior.
A Thorough View of Exact Inference in Graphs from the Degree-4 Sum-of-Squares Hierarchy
Performing inference in graphs is a common task within several machine learning problems, e. g., image segmentation, community detection, among others.
Information Theoretic Limits of Exact Recovery in Sub-hypergraph Models for Community Detection
Our bounds are tight and pertain to the community detection problems in various models such as the planted hypergraph stochastic block model, the planted densest sub-hypergraph model, and the planted multipartite hypergraph model.
Randomized Deep Structured Prediction for Discourse-Level Processing
In this paper, we explore the use of randomized inference to alleviate this concern and show that we can efficiently leverage deep structured prediction and expressive neural encoders for a set of tasks involving complicated argumentative structures.
A Le Cam Type Bound for Adversarial Learning and Applications
Robustness of machine learning methods is essential for modern practical applications.
Fairness constraints can help exact inference in structured prediction
Given a generative model with an undirected connected graph $G$ and true vector of binary labels, it has been previously shown that when $G$ has good expansion properties, such as complete graphs or $d$-regular expanders, one can exactly recover the true labels (with high probability and in polynomial time) from a single noisy observation of each edge and node.
Information Theoretic Lower Bounds for Feed-Forward Fully-Connected Deep Networks
In this paper, we study the sample complexity lower bounds for the exact recovery of parameters and for a positive excess risk of a feed-forward, fully-connected neural network for binary classification, using information-theoretic tools.
Meta Learning for Support Recovery in High-dimensional Precision Matrix Estimation
Then for the novel task, we prove that the minimization of the $\ell_1$-regularized log-determinant Bregman divergence with the additional constraint that the support is a subset of the estimated support union could reduce the sufficient sample complexity of successful support recovery to $O(\log(|S_{\text{off}}|))$ where $|S_{\text{off}}|$ is the number of off-diagonal elements in the support union and is much less than $N$ for sparse matrices.
Exact Support Recovery in Federated Regression with One-shot Communication
Federated learning provides a framework to address the challenges of distributed computing, data ownership and privacy over a large number of distributed clients with low computational and communication capabilities.
Exact Partitioning of High-order Planted Models with a Tensor Nuclear Norm Constraint
We study the problem of efficient exact partitioning of the hypergraphs generated by high-order planted models.
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.
Information-Theoretic Lower Bounds for Zero-Order Stochastic Gradient Estimation
In this paper we analyze the necessary number of samples to estimate the gradient of any multidimensional smooth (possibly non-convex) function in a zero-order stochastic oracle model.
First Order Methods take Exponential Time to Converge to Global Minimizers of Non-Convex Functions
We show that the parameter estimation problem is equivalent to the problem of function identification in the given family.
Novel Change of Measure Inequalities with Applications to PAC-Bayesian Bounds and Monte Carlo Estimation
We introduce several novel change of measure inequalities for two families of divergences: $f$-divergences and $\alpha$-divergences.
The Sample Complexity of Meta Sparse Regression
A key difference between meta-learning and the classical multi-task learning, is that meta-learning focuses only on the recovery of the parameters of the novel task, while multi-task learning estimates the parameter of all tasks, which requires l to grow with T .
Provable Computational and Statistical Guarantees for Efficient Learning of Continuous-Action Graphical Games
We propose a $\ell_{12}-$ block regularized method which recovers a graphical game, whose Nash equilibria are the $\epsilon$-Nash equilibria of the game from which the data was generated (true game).
Exact Partitioning of High-order Models with a Novel Convex Tensor Cone Relaxation
In this paper we propose an algorithm for exact partitioning of high-order models.
Direct Learning with Guarantees of the Difference DAG Between Structural Equation Models
Discovering cause-effect relationships between variables from observational data is a fundamental challenge in many scientific disciplines.
On the Correctness and Sample Complexity of Inverse Reinforcement Learning
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.
Exact inference in structured prediction
Our results show that exact recovery is possible and achievable in polynomial time for a large class of graphs.
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.
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.
Exact Inference with Latent Variables in an Arbitrary Domain
We analyze the necessary and sufficient conditions for exact inference of a latent model.
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.
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.
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.
Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time
In this paper, we propose a provably polynomial time randomized algorithm for learning the parameters of perturbed MAP predictors.
Regularized Loss Minimizers with Local Data Perturbation: Consistency and Data Irrecoverability
We introduce a new concept, data irrecoverability, and show that the well-studied concept of data privacy is sufficient but not necessary for data irrecoverability.
Learning discrete Bayesian networks in polynomial time and sample complexity
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.
Information-theoretic Limits for Community Detection in Network Models
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.
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.
The Error Probability of Random Fourier Features is Dimensionality Independent
We show that the error probability of reconstructing kernel matrices from Random Fourier Features for the Gaussian kernel function is at most $\mathcal{O}(R^{2/3} \exp(-D))$, where $D$ is the number of random features and $R$ is the diameter of the data domain.
Learning linear structural equation models in polynomial time and sample complexity
We develop a new algorithm --- which is computationally and statistically efficient and works in the high-dimensional regime --- for learning linear SEMs from purely observational data with arbitrary noise distribution.
Learning Sparse Polymatrix Games in Polynomial Time and Sample Complexity
We also show that $\Omega(d \log (pm))$ 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.
Computationally and statistically efficient learning of causal Bayes nets using path queries
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.
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.
Learning Identifiable Gaussian Bayesian Networks in Polynomial Time and Sample Complexity
In this paper we propose a provably polynomial-time algorithm for learning sparse Gaussian Bayesian networks with equal noise variance --- a class of Bayesian networks for which the DAG structure can be uniquely identified from observational data --- under high-dimensional settings.
Learning Graphical Games from Behavioral Data: Sufficient and Necessary Conditions
In this paper we obtain sufficient and necessary conditions on the number of samples required for exact recovery of the pure-strategy Nash equilibria (PSNE) set of a graphical game from noisy observations of joint actions.
Information Theoretic Limits for Linear Prediction with Graph-Structured Sparsity
We analyze the necessary number of samples for sparse vector recovery in a noisy linear prediction setup.
From Behavior to Sparse Graphical Games: Efficient Recovery of Equilibria
In this paper we study the problem of exact recovery of the pure-strategy Nash equilibria (PSNE) set of a graphical game from noisy observations of joint actions of the players alone.
Information-Theoretic Lower Bounds for Recovery of Diffusion Network Structures
We study the information-theoretic lower bound of the sample complexity of the correct recovery of diffusion network structures.
Information-theoretic limits of Bayesian network structure learning
In this paper, we study the information-theoretic limits of learning the structure of Bayesian networks (BNs), on discrete as well as continuous random variables, from a finite number of samples.
On the Sample Complexity of Learning Graphical Games
By using information-theoretic arguments, we show that if the number of samples is less than ${\Omega(k n \log^2{n})}$ for sparse graphs or ${\Omega(n^2 \log{n})}$ for dense graphs, then any conceivable method fails to recover the PSNE with arbitrary probability.
Structured Prediction: From Gaussian Perturbations to Linear-Time Principled Algorithms
Thus, using the maximum loss over random structured outputs is a principled way of learning the parameter of structured prediction models.
Inverse Covariance Estimation for High-Dimensional Data in Linear Time and Space: Spectral Methods for Riccati and Sparse Models
Furthermore, instead of obtaining a single solution for a specific regularization parameter, our algorithm finds the whole solution path.
On the Statistical Efficiency of $\ell_{1,p}$ Multi-Task Learning of Gaussian Graphical Models
In this paper, we present $\ell_{1, p}$ multi-task structure learning for Gaussian graphical models.
Two-person interaction detection using body-pose features and multiple instance learning
Human activity recognition has potential to impact a wide range of applications from surveillance to human computer interfaces to content based video retrieval.
Learning the Structure and Parameters of Large-Population Graphical Games from Behavioral Data
We consider learning, from strictly behavioral data, the structure and parameters of linear influence games (LIGs), a class of parametric graphical games introduced by Irfan and Ortiz (2014).
Sparse and Locally Constant Gaussian Graphical Models
Locality information is crucial in datasets where each variable corresponds to a measurement in a manifold (silhouettes, motion trajectories, 2D and 3D images).
