Search Results for author:
Found 105 papers, 8 papers with code
FedBoost: A Communication-Efficient Algorithm for Federated Learning
We provide communication-efficient ensemble algorithms for federated learning, where per-round communication cost is independent of the size of the ensemble.
Online Learning with Dependent Stochastic Feedback Graphs
A general framework for online learning with partial information is one where feedback graphs specify which losses can be observed by the learner.
Enhanced $H$-Consistency Bounds
Recent research has introduced a key notion of $H$-consistency bounds for surrogate losses.
Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
We present a comprehensive study of surrogate loss functions for learning to defer.
Multi-Label Learning with Stronger Consistency Guarantees
We also extend our multi-label logistic losses to more comprehensive multi-label comp-sum losses, adapting comp-sum losses from standard classification to the multi-label learning.
Cardinality-Aware Set Prediction and Top-$k$ Classification
We introduce a new target loss function tailored to this setting that accounts for both the classification error and the cardinality of the set predicted.
Rate-Preserving Reductions for Blackwell Approachability
Abernethy et al. (2011) showed that Blackwell approachability and no-regret learning are equivalent, in the sense that any algorithm that solves a specific Blackwell approachability instance can be converted to a sublinear regret algorithm for a specific no-regret learning instance, and vice versa.
A Universal Growth Rate for Learning with Smooth Surrogate Losses
This paper presents a comprehensive analysis of the growth rate of $H$-consistency bounds (and excess error bounds) for various surrogate losses used in classification.
Regression with Multi-Expert Deferral
In this work, we introduce a novel framework of regression with deferral, which involves deferring the prediction to multiple experts.
Top-$k$ Classification and Cardinality-Aware Prediction
For these functions, we derive cost-sensitive comp-sum and constrained surrogate losses, establishing their $H$-consistency bounds and Bayes-consistency.
$H$-Consistency Guarantees for Regression
Next, we prove a series of novel $H$-consistency bounds for surrogate loss functions of the squared loss, under the assumption of a symmetric distribution and a bounded hypothesis set.
Principled Approaches for Learning to Defer with Multiple Experts
We present a study of surrogate losses and algorithms for the general problem of learning to defer with multiple experts.
Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention
We introduce new families of surrogate losses for the abstention loss function, which include the state-of-the-art surrogate losses in the single-stage setting and a novel family of loss functions in the two-stage setting.
Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms
We study the key framework of learning with abstention in the multi-class classification setting.
Ranking with Abstention
We introduce a novel framework of ranking with abstention, where the learner can abstain from making prediction at some limited cost $c$.
Differentially Private Domain Adaptation with Theoretical Guarantees
This is the modern problem of supervised domain adaptation from a public source to a private target domain.
Best-Effort Adaptation
We show how these bounds can guide the design of learning algorithms that we discuss in detail.
Cross-Entropy Loss Functions: Theoretical Analysis and Applications
These are non-asymptotic guarantees that upper bound the zero-one loss estimation error in terms of the estimation error of a surrogate loss, for the specific hypothesis set $H$ used.
Pseudonorm Approachability and Applications to Regret Minimization
We then use that to show, modulo mild normalization assumptions, that there exists an $\ell_\infty$-approachability algorithm whose convergence is independent of the dimension of the original vectorial payoff.
A Provably Efficient Model-Free Posterior Sampling Method for Episodic Reinforcement Learning
Thompson Sampling is one of the most effective methods for contextual bandits and has been generalized to posterior sampling for certain MDP settings.
Private Domain Adaptation from a Public Source
A key problem in a variety of applications is that of domain adaptation from a public source domain, for which a relatively large amount of labeled data with no privacy constraints is at one's disposal, to a private target domain, for which a private sample is available with very few or no labeled data.
Stochastic Online Learning with Feedback Graphs: Finite-Time and Asymptotic Optimality
We revisit the problem of stochastic online learning with feedback graphs, with the goal of devising algorithms that are optimal, up to constants, both asymptotically and in finite time.
Guarantees for Epsilon-Greedy Reinforcement Learning with Function Approximation
This paper presents a theoretical analysis of such policies and provides the first regret and sample-complexity bounds for reinforcement learning with myopic exploration.
Strategizing against Learners in Bayesian Games
We study repeated two-player games where one of the players, the learner, employs a no-regret learning strategy, while the other, the optimizer, is a rational utility maximizer.
$\mathscr{H}$-Consistency Estimation Error of Surrogate Loss Minimizers
We also show that previous excess error bounds can be recovered as special cases of our general results.
Differentially Private Learning with Margin Guarantees
For the family of linear hypotheses, we give a pure DP learning algorithm that benefits from relative deviation margin guarantees, as well as an efficient DP learning algorithm with margin guarantees.
On the Existence of the Adversarial Bayes Classifier (Extended Version)
Our results can provide a useful tool for a subsequent study of surrogate losses in adversarial robustness and their consistency properties.
Breaking the centralized barrier for cross-device federated learning
Federated learning (FL) is a challenging setting for optimization due to the heterogeneity of the data across different clients which gives rise to the client drift phenomenon.
On the Existence of The Adversarial Bayes Classifier
Adversarial robustness is a critical property in a variety of modern machine learning applications.
Boosting with Multiple Sources
We study the problem of learning accurate ensemble predictors, in particular boosting, in the presence of multiple source domains.
A Field Guide to Federated Optimization
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection.
Adapting to Misspecification in Contextual Bandits
Given access to an online oracle for square loss regression, our algorithm attains optimal regret and -- in particular -- optimal dependence on the misspecification level, with no prior knowledge.
Beyond Value-Function Gaps: Improved Instance-Dependent Regret Bounds for Episodic Reinforcement Learning
Our results show that optimistic algorithms can not achieve the information-theoretic lower bounds even in deterministic MDPs unless there is a unique optimal policy.
Agnostic Reinforcement Learning with Low-Rank MDPs and Rich Observations
In this work, we consider the more realistic setting of agnostic RL with rich observation spaces and a fixed class of policies $\Pi$ that may not contain any near-optimal policy.
A Finer Calibration Analysis for Adversarial Robustness
Moreover, our calibration results, combined with the previous study of consistency by Awasthi et al. (2021), also lead to more general $H$-consistency results covering common hypothesis sets.
Calibration and Consistency of Adversarial Surrogate Losses
We then give a characterization of H-calibration and prove that some surrogate losses are indeed H-calibrated for the adversarial loss, with these hypothesis sets.
Communication-Efficient Agnostic Federated Averaging
We propose a communication-efficient distributed algorithm called Agnostic Federated Averaging (or AgnosticFedAvg) to minimize the domain-agnostic objective proposed in Mohri et al. (2019), which is amenable to other private mechanisms such as secure aggregation.
Learning with User-Level Privacy
We show that for high-dimensional mean estimation, empirical risk minimization with smooth losses, stochastic convex optimization, and learning hypothesis classes with finite metric entropy, the privacy cost decreases as $O(1/\sqrt{m})$ as users provide more samples.
PAC-Bayes Learning Bounds for Sample-Dependent Priors
We present a series of new PAC-Bayes learning guarantees for randomized algorithms with sample-dependent priors.
Agnostic Learning with Multiple Objectives
We further implement the algorithm in a popular symbolic gradient computation framework and empirically demonstrate on a number of datasets the benefits of $\almo$ framework versus learning with a fixed mixture weights distribution.
A Discriminative Technique for Multiple-Source Adaptation
We present a new discriminative technique for the multiple-source adaptation, MSA, problem.
Beyond Individual and Group Fairness
In the adversarial setting, we design efficient algorithms with competitive ratio guarantees.
Mime: Mimicking Centralized Stochastic Algorithms in Federated Learning
Federated learning (FL) is a challenging setting for optimization due to the heterogeneity of the data across different clients which gives rise to the client drift phenomenon.
On the Rademacher Complexity of Linear Hypothesis Sets
Linear predictors form a rich class of hypotheses used in a variety of learning algorithms.
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data
We present a theoretical and algorithmic study of the multiple-source domain adaptation problem in the common scenario where the learner has access only to a limited amount of labeled target data, but where the learner has at disposal a large amount of labeled data from multiple source domains.
Relative Deviation Margin Bounds
We present a series of new and more favorable margin-based learning guarantees that depend on the empirical margin loss of a predictor.
Corralling Stochastic Bandit Algorithms
We study the problem of corralling stochastic bandit algorithms, that is combining multiple bandit algorithms designed for a stochastic environment, with the goal of devising a corralling algorithm that performs almost as well as the best base algorithm.
Reinforcement Learning with Feedback Graphs
We study episodic reinforcement learning in Markov decision processes when the agent receives additional feedback per step in the form of several transition observations.
Adversarial Learning Guarantees for Linear Hypotheses and Neural Networks
We give upper and lower bounds for the adversarial empirical Rademacher complexity of linear hypotheses with adversarial perturbations measured in $l_r$-norm for an arbitrary $r \geq 1$.
Three Approaches for Personalization with Applications to Federated Learning
The standard objective in machine learning is to train a single model for all users.
Adaptive Region-Based Active Learning
We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, both phases actively requesting labels.
Advances and Open Problems in Federated Learning
FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches.
Regularized Gradient Boosting
We fill this gap by deriving data-dependent learning guarantees for \GB\ used with \emph{regularization}, expressed in terms of the Rademacher complexities of the constrained families of base predictors.
Learning GANs and Ensembles Using Discrepancy
Generative adversarial networks (GANs) generate data based on minimizing a divergence between two distributions.
SCAFFOLD: Stochastic Controlled Averaging for Federated Learning
We obtain tight convergence rates for FedAvg and prove that it suffers from `client-drift' when the data is heterogeneous (non-iid), resulting in unstable and slow convergence.
Bandits with Feedback Graphs and Switching Costs
We give a new algorithm whose regret guarantee depends only on the domination number of the graph.
AdaNet: A Scalable and Flexible Framework for Automatically Learning Ensembles
AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention.
Hypothesis Set Stability and Generalization
Our main result is a generalization bound for data-dependent hypothesis sets expressed in terms of a notion of hypothesis set stability and a notion of Rademacher complexity for data-dependent hypothesis sets that we introduce.
Agnostic Federated Learning
A key learning scenario in large-scale applications is that of federated learning, where a centralized model is trained based on data originating from a large number of clients.
Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses
In this paper, we design efficient gradient computation algorithms for two broad families of structured prediction loss functions: rational and tropical losses.
Policy Regret in Repeated Games
We revisit the notion of policy regret and first show that there are online learning settings in which policy regret and external regret are incompatible: any sequence of play that achieves a favorable regret with respect to one definition must do poorly with respect to the other.
Algorithms and Theory for Multiple-Source Adaptation
This work includes a number of novel contributions for the multiple-source adaptation problem.
Online Non-Additive Path Learning under Full and Partial Information
We study the problem of online path learning with non-additive gains, which is a central problem appearing in several applications, including ensemble structured prediction.
Logistic Regression: The Importance of Being Improper
Starting with the simple observation that the logistic loss is $1$-mixable, we design a new efficient improper learning algorithm for online logistic regression that circumvents the aforementioned lower bound with a regret bound exhibiting a doubly-exponential improvement in dependence on the predictor norm.
Theory and Algorithms for Forecasting Time Series
We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes.
Parameter-free online learning via model selection
We introduce an efficient algorithmic framework for model selection in online learning, also known as parameter-free online learning.
Discriminative State Space Models
In this paper, we introduce and analyze Discriminative State-Space Models for forecasting non-stationary time series.
Online Learning with Transductive Regret
A by-product of our study is an algorithm for swap regret, which, under mild assumptions, is more efficient than existing ones, and a substantially more efficient algorithm for time selection swap regret.
Multiple-Source Adaptation for Regression Problems
We present a detailed theoretical analysis of the problem of multiple-source adaptation in the general stochastic scenario, extending known results that assume a single target labeling function.
Discrepancy-Based Algorithms for Non-Stationary Rested Bandits
We show that the notion of discrepancy can be used to design very general algorithms and a unified framework for the analysis of multi-armed rested bandit problems with non-stationary rewards.
Online Learning with Automata-based Expert Sequences
We consider a general framework of online learning with expert advice where regret is defined with respect to sequences of experts accepted by a weighted automaton.
Online Learning with Abstention
In the stochastic setting, we first point out a bias problem that limits the straightforward extension of algorithms such as UCB-N to time-varying feedback graphs, as needed in this context.
Optimistic Bandit Convex Optimization
We introduce the general and powerful scheme of predicting information re-use in optimization algorithms.
Boosting with Abstention
We present a new boosting algorithm for the key scenario of binary classification with abstention where the algorithm can abstain from predicting the label of a point, at the price of a fixed cost.
Generalization Bounds for Weighted Automata
We present new data-dependent generalization guarantees for learning weighted automata expressed in terms of the Rademacher complexity of these families.
AdaNet: Adaptive Structural Learning of Artificial Neural Networks
We present new algorithms for adaptively learning artificial neural networks.
Structured Prediction Theory Based on Factor Graph Complexity
We give new data-dependent margin guarantees for structured prediction for a very wide family of loss functions and a general family of hypotheses, with an arbitrary factor graph decomposition.
Revenue Optimization against Strategic Buyers
We present a revenue optimization algorithm for posted-price auctions when facing a buyer with random valuations who seeks to optimize his $\gamma$-discounted surplus.
Learning Theory and Algorithms for Forecasting Non-stationary Time Series
We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes.
Foundations of Coupled Nonlinear Dimensionality Reduction
The generalization error bound is based on a careful analysis of the empirical Rademacher complexity of the relevant hypothesis set.
Accelerating Optimization via Adaptive Prediction
We present a powerful general framework for designing data-dependent optimization algorithms, building upon and unifying recent techniques in adaptive regularization, optimistic gradient predictions, and problem-dependent randomization.
Voted Kernel Regularization
This paper presents an algorithm, Voted Kernel Regularization , that provides the flexibility of using potentially very complex kernel functions such as predictors based on much higher-degree polynomial kernels, while benefitting from strong learning guarantees.
Non-parametric Revenue Optimization for Generalized Second Price Auctions
To our knowledge, this is the first attempt to apply learning algorithms to the problem of reserve price optimization in GSP auctions.
Multi-Class Deep Boosting
We give new data-dependent learning bounds for convex ensembles in the multi-class classification setting expressed in terms of the Rademacher complexities of the sub-families composing the base classifier set, and the mixture weight assigned to each sub-family.
Optimal Regret Minimization in Posted-Price Auctions with Strategic Buyers
We study revenue optimization learning algorithms for posted-price auctions with strategic buyers.
Conditional Swap Regret and Conditional Correlated Equilibrium
We introduce a natural extension of the notion of swap regret, conditional swap regret, that allows for action modifications conditioned on the player’s action history.
Revenue Optimization in Posted-Price Auctions with Strategic Buyers
We study revenue optimization learning algorithms for posted-price auctions with strategic buyers.
Adaptation Algorithm and Theory Based on Generalized Discrepancy
We present a new algorithm for domain adaptation improving upon a discrepancy minimization algorithm previously shown to outperform a number of algorithms for this task.
Learning Kernels Using Local Rademacher Complexity
We use the notion of local Rademacher complexity to design new algorithms for learning kernels.
Relative Deviation Learning Bounds and Generalization with Unbounded Loss Functions
We present an extensive analysis of relative deviation bounds, including detailed proofs of two-sided inequalities and their implications.
Learning Theory and Algorithms for Revenue Optimization in Second-Price Auctions with Reserve
Second-price auctions with reserve play a critical role for modern search engine and popular online sites since the revenue of these companies often directly de- pends on the outcome of such auctions.
Tight Lower Bound on the Probability of a Binomial Exceeding its Expectation
We give the proof of a tight lower bound on the probability that a binomial random variable exceeds its expected value.
Perceptron Mistake Bounds
We present a brief survey of existing mistake bounds and introduce novel bounds for the Perceptron or the kernel Perceptron algorithm.
Accuracy at the Top
We introduce a new notion of classification accuracy based on the top $\tau$-quantile values of a scoring function, a relevant criterion in a number of problems arising for search engines.
Algorithms for Learning Kernels Based on Centered Alignment
Our theoretical results include a novel concentration bound for centered alignment between kernel matrices, the proof of the existence of effective predictors for kernels with high alignment, both for classification and for regression, and the proof of stability-based generalization bounds for a broad family of algorithms for learning kernels based on centered alignment.
Learning Bounds for Importance Weighting
This paper presents an analysis of importance weighting for learning from finite samples and gives a series of theoretical and algorithmic results.
Polynomial Semantic Indexing
We present a class of nonlinear (polynomial) models that are discriminatively trained to directly map from the word content in a query-document or document-document pair to a ranking score.
Learning Non-Linear Combinations of Kernels
This paper studies the general problem of learning kernels based on a polynomial combination of base kernels.
Ensemble Nystrom Method
A crucial technique for scaling kernel methods to very large data sets reaching or exceeding millions of instances is based on low-rank approximation of kernel matrices.
Efficient Large-Scale Distributed Training of Conditional Maximum Entropy Models
Training conditional maximum entropy models on massive data requires significant time and computational resources.
Domain Adaptation: Learning Bounds and Algorithms
This motivates our analysis of the problem of minimizing the empirical discrepancy for various loss functions for which we also give novel algorithms.
Rademacher Complexity Bounds for Non-I.I.D. Processes
In particular, they are data-dependent and measure the complexity of a class of hypotheses based on the training sample.
Domain Adaptation with Multiple Sources
The problem consists of combining these hypotheses to derive a hypothesis with small error with respect to the target domain.
Stability Bounds for Non-i.i.d. Processes
We also illustrate their application in the case of several general classes of learning algorithms, including Support Vector Regression and Kernel Ridge Regression.
