Search Results for author:
Found 68 papers, 8 papers with code
Provable Hyperparameter Tuning for Structured Pfaffian Settings
We then show that for many parameterized algorithms of interest, their utility function possesses a refined piece-wise structure, which automatically translates to learning guarantees using our proposed framework.
Subsidy design for better social outcomes
Overcoming the impact of selfish behavior of rational players in multiagent systems is a fundamental problem in game theory.
Regret Minimization in Stackelberg Games with Side Information
In sharp contrast to the non-contextual version, we show that it is impossible for the leader to achieve good performance (measured by regret) in the full adversarial setting.
Spectrally Transformed Kernel Regression
Unlabeled data is a key component of modern machine learning.
Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
For this method, we prove that a bandit online learning algorithm--using only the number of iterations as feedback--can select parameters for a sequence of instances such that the overall cost approaches that of the best fixed $\omega$ as the sequence length increases.
Learning with Explanation Constraints
In this paper, we formalize this notion as learning from explanation constraints and provide a learning theoretic framework to analyze how such explanations can improve the learning of our models.
New Guarantees for Learning Revenue Maximizing Menus of Lotteries and Two-Part Tariffs
We provide the first online learning algorithms for menus of lotteries and two-part tariffs with strong regret-bound guarantees.
Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games
Adversarial training is a standard technique for training adversarially robust models.
Label Propagation with Weak Supervision
Semi-supervised learning and weakly supervised learning are important paradigms that aim to reduce the growing demand for labeled data in current machine learning applications.
Provably tuning the ElasticNet across instances
We consider the problem of tuning the regularization parameters of Ridge regression, LASSO, and the ElasticNet across multiple problem instances, a setting that encompasses both cross-validation and multi-task hyperparameter optimization.
Meta-Learning Adversarial Bandits
We study online learning with bandit feedback across multiple tasks, with the goal of improving average performance across tasks if they are similar according to some natural task-similarity measure.
Structural Analysis of Branch-and-Cut and the Learnability of Gomory Mixed Integer Cuts
These guarantees apply to infinite families of cutting planes, such as the family of Gomory mixed integer cuts, which are responsible for the main breakthrough speedups of integer programming solvers.
Output-sensitive ERM-based techniques for data-driven algorithm design
Data-driven algorithm design is a promising, learning-based approach for beyond worst-case analysis of algorithms with tunable parameters.
Robustly-reliable learners under poisoning attacks
Remarkably, we provide a complete characterization of learnability in this setting, in particular, nearly-tight matching upper and lower bounds on the region that can be certified, as well as efficient algorithms for computing this region given an ERM oracle.
Learning Predictions for Algorithms with Predictions
A burgeoning paradigm in algorithm design is the field of algorithms with predictions, in which algorithms can take advantage of a possibly-imperfect prediction of some aspect of the problem.
Improved Sample Complexity Bounds for Branch-and-Cut
If the training set is too small, a configuration may have good performance over the training set but poor performance on future integer programs.
Learning-to-learn non-convex piecewise-Lipschitz functions
We analyze the meta-learning of the initialization and step-size of learning algorithms for piecewise-Lipschitz functions, a non-convex setting with applications to both machine learning and algorithms.
Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing
Tuning hyperparameters is a crucial but arduous part of the machine learning pipeline.
Sample Complexity of Tree Search Configuration: Cutting Planes and Beyond
We first bound the sample complexity of learning cutting planes from the canonical family of Chv\'atal-Gomory cuts.
Data driven semi-supervised learning
Over the past decades, several elegant graph-based semi-supervised learning algorithms for how to infer the labels of the unlabeled examples given the graph and a few labeled examples have been proposed.
Generalization in portfolio-based algorithm selection
This algorithm configuration procedure works by first selecting a portfolio of diverse algorithm parameter settings, and then, on a given problem instance, using an algorithm selector to choose a parameter setting from the portfolio with strong predicted performance.
Scalable and Provably Accurate Algorithms for Differentially Private Distributed Decision Tree Learning
We provide the first utility guarantees for differentially private top-down decision tree learning in both the single machine and distributed settings.
Data-driven Algorithm Design
Data driven algorithm design is an important aspect of modern data science and algorithm design.
An Analysis of Robustness of Non-Lipschitz Networks
Despite significant advances, deep networks remain highly susceptible to adversarial attack.
Noise in Classification
This chapter considers the computational and statistical aspects of learning linear thresholds in presence of noise.
Refined bounds for algorithm configuration: The knife-edge of dual class approximability
We answer this question for algorithm configuration problems that exhibit a widely-applicable structure: the algorithm's performance as a function of its parameters can be approximated by a "simple" function.
Geometry-Aware Gradient Algorithms for Neural Architecture Search
Recent state-of-the-art methods for neural architecture search (NAS) exploit gradient-based optimization by relaxing the problem into continuous optimization over architectures and shared-weights, a noisy process that remains poorly understood.
On Weight-Sharing and Bilevel Optimization in Architecture Search
Weight-sharing—the simultaneous optimization of multiple neural networks using the same parameters—has emerged as a key component of state-of-the-art neural architecture search.
How much data is sufficient to learn high-performing algorithms? Generalization guarantees for data-driven algorithm design
We provide a broadly applicable theory for deriving generalization guarantees that bound the difference between the algorithm's average performance over the training set and its expected performance.
Learning piecewise Lipschitz functions in changing environments
We consider the class of piecewise Lipschitz functions, which is the most general online setting considered in the literature for the problem, and arises naturally in various combinatorial algorithm selection problems where utility functions can have sharp discontinuities.
Learning to Link
Clustering is an important part of many modern data analysis pipelines, including network analysis and data retrieval.
Adaptive Gradient-Based Meta-Learning Methods
We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential prediction algorithms.
Learning to Optimize Computational Resources: Frugal Training with Generalization Guarantees
Our algorithm can help compile a configuration portfolio, or it can be used to select the input to a configuration algorithm for finite parameter spaces.
Semi-bandit Optimization in the Dispersed Setting
We apply our semi-bandit results to obtain the first provable guarantees for data-driven algorithm design for linkage-based clustering and we improve the best regret bounds for designing greedy knapsack algorithms.
Provable Guarantees for Gradient-Based Meta-Learning
We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods.
Testing Matrix Rank, Optimally
This improves upon the previous $O(d^2/\epsilon^2)$ bound (SODA'03), and bypasses an $\Omega(d^2/\epsilon^2)$ lower bound of (KDD'14) which holds if the algorithm is required to read a submatrix.
Envy-Free Classification
In classic fair division problems such as cake cutting and rent division, envy-freeness requires that each individual (weakly) prefer his allocation to anyone else's.
Data-Driven Clustering via Parameterized Lloyd's Families
Algorithms for clustering points in metric spaces is a long-studied area of research.
Learning to Branch
Tree search algorithms recursively partition the search space to find an optimal solution.
Dispersion for Data-Driven Algorithm Design, Online Learning, and Private Optimization
We present general techniques for online and private optimization of the sum of dispersed piecewise Lipschitz functions.
Risk Bounds for Transferring Representations With and Without Fine-Tuning
If the representation learned from the source task is fixed, we identify conditions on how the tasks relate to obtain an upper bound on target task risk via a VC dimension-based argument.
Differentially Private Clustering in High-Dimensional Euclidean Spaces
We study the problem of clustering sensitive data while preserving the privacy of individuals represented in the dataset, which has broad applications in practical machine learning and data analysis tasks.
Lifelong Learning in Costly Feature Spaces
An important long-term goal in machine learning systems is to build learning agents that, like humans, can learn many tasks over their lifetime, and moreover use information from these tasks to improve their ability to do so efficiently.
Clustering under Local Stability: Bridging the Gap between Worst-Case and Beyond Worst-Case Analysis
The typical idea is to design a clustering algorithm that outputs a near-optimal solution, provided the data satisfy a natural stability notion.
Generalization Guarantees for Multi-item Profit Maximization: Pricing, Auctions, and Randomized Mechanisms
We study multi-item profit maximization when there is an underlying distribution over buyers' values.
Matrix Completion and Related Problems via Strong Duality
This work studies the strong duality of non-convex matrix factorization problems: we show that under certain dual conditions, these problems and its dual have the same optimum.
Sample and Computationally Efficient Learning Algorithms under S-Concave Distributions
In this work, we introduce new convex geometry tools to study the properties of $s$-concave distributions and use these properties to provide bounds on quantities of interest to learning including the probability of disagreement between two halfspaces, disagreement outside a band, and the disagreement coefficient.
Robust Communication-Optimal Distributed Clustering Algorithms
In this work, we study the $k$-median and $k$-means clustering problems when the data is distributed across many servers and can contain outliers.
Scalable Influence Maximization for Multiple Products in Continuous-Time Diffusion Networks
A typical viral marketing model identifies influential users in a social network to maximize a single product adoption assuming unlimited user attention, campaign budgets, and time.
Noise-Tolerant Life-Long Matrix Completion via Adaptive Sampling
For this problem, we present an algorithm that returns a matrix of a small error, with sample complexity almost as small as the best prior results in the noiseless case.
Learning-Theoretic Foundations of Algorithm Configuration for Combinatorial Partitioning Problems
We address this problem for clustering, max-cut, and other partitioning problems, such as integer quadratic programming, by designing computationally efficient and sample efficient learning algorithms which receive samples from an application-specific distribution over problem instances and learn a partitioning algorithm with high expected performance.
Sample Complexity of Automated Mechanism Design
In the traditional economic models, it is assumed that the bidders' valuations are drawn from an underlying distribution and that the auction designer has perfect knowledge of this distribution.
Learning Combinatorial Functions from Pairwise Comparisons
However, for real-valued functions, cardinal labels might not be accessible, or it may be difficult for an expert to consistently assign real-valued labels over the entire set of examples.
Active Learning Algorithms for Graphical Model Selection
The problem of learning the structure of a high dimensional graphical model from data has received considerable attention in recent years.
Communication Efficient Distributed Agnostic Boosting
We consider the problem of learning from distributed data in the agnostic setting, i. e., in the presence of arbitrary forms of noise.
$k$-center Clustering under Perturbation Resilience
In this work, we take this approach and provide strong positive results both for the asymmetric and symmetric $k$-center problems under a natural input stability (promise) condition called $\alpha$-perturbation resilience [Bilu and Linia 2012], which states that the optimal solution does not change under any alpha-factor perturbation to the input distances.
Learning Cooperative Games
This paper explores a PAC (probably approximately correct) learning model in cooperative games.
Computer Science and Game Theory
Communication Efficient Distributed Kernel Principal Component Analysis
Can we perform kernel PCA on the entire dataset in a distributed and communication efficient fashion while maintaining provable and strong guarantees in solution quality?
Efficient Learning of Linear Separators under Bounded Noise
We provide the first polynomial time algorithm that can learn linear separators to arbitrarily small excess error in this noise model under the uniform distribution over the unit ball in $\Re^d$, for some constant value of $\eta$.
Efficient Representations for Life-Long Learning and Autoencoding
Specifically, we consider the problem of learning many different target functions over time, that share certain commonalities that are initially unknown to the learning algorithm.
Improved Distributed Principal Component Analysis
We give new algorithms and analyses for distributed PCA which lead to improved communication and computational costs for $k$-means clustering and related problems.
Efficient Clustering with Limited Distance Information
Given a point set S and an unknown metric d on S, we study the problem of efficiently partitioning S into k clusters while querying few distances between the points.
Learning Economic Parameters from Revealed Preferences
In this work we advance this line of work by providing sample complexity guarantees and efficient algorithms for a number of important classes.
Scalable Kernel Methods via Doubly Stochastic Gradients
The general perception is that kernel methods are not scalable, and neural nets are the methods of choice for nonlinear learning problems.
Active Learning and Best-Response Dynamics
We examine an important setting for engineered systems in which low-power distributed sensors are each making highly noisy measurements of some unknown target function.
A Distributed Frank-Wolfe Algorithm for Communication-Efficient Sparse Learning
We further show that the communication cost of dFW is optimal by deriving a lower-bound on the communication cost required to construct an $\epsilon$-approximate solution.
Robust Hierarchical Clustering
One of the most widely used techniques for data clustering is agglomerative clustering.
Local algorithms for interactive clustering
We study the design of interactive clustering algorithms for data sets satisfying natural stability assumptions.
