arXiv subjects

Mehryar Mohri

Publications and source records attributed to Mehryar Mohri.

At least 109 records · Page 6Linked to original sources

arXiv2016

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. We also give detailed proofs of two-sided generalization bounds that hold in the general case of unbounded loss functions, under the assumption that a moment of the loss is bounded. These bounds are useful in the analysis of importance weighting and other learning tasks such as unbounded regression.

cs.LG↗

arXiv2015

Foundations of Coupled Nonlinear Dimensionality Reduction

In this paper we introduce and analyze the learning scenario of \emph{coupled nonlinear dimensionality reduction}, which combines two major steps of machine learning pipeline: projection onto a manifold and subsequent supervised learning. First, we present new generalization bounds for this scenario and, second, we introduce an algorithm that follows from these bounds. The generalization error bound is based on a careful analysis of the empirical Rademacher complexity of the relevant hypothesis set. In particular, we show an upper bound on the Rademacher complexity that is in $\widetilde O(\sqrt{Λ_{(r)}/m})$, where $m$ is the sample size and $Λ_{(r)}$ the upper bound on the Ky-Fan $r$-norm of the associated kernel matrix. We give both upper and lower bound guarantees in terms of that Ky-Fan $r$-norm, which strongly justifies the definition of our hypothesis set. To the best of our knowledge, these are the first learning guarantees for the problem of coupled dimensionality reduction. Our analysis and learning guarantees further apply to several special cases, such as that of using a fixed kernel with supervised dimensionality reduction or that of unsupervised learning of a kernel for dimensionality reduction followed by a supervised learning algorithm. Based on theoretical analysis, we suggest a structural risk minimization algorithm consisting of the coupled fitting of a low dimensional manifold and a separation function on that manifold.

stat.ML↗

arXiv2015

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. We first present a series of new regret guarantees that hold at any time and under very minimal assumptions, and then show how different relaxations recover existing algorithms, both basic as well as more recent sophisticated ones. Finally, we show how combining adaptivity, optimism, and problem-dependent randomization can guide the design of algorithms that benefit from more favorable guarantees than recent state-of-the-art methods.

stat.ML↗

arXiv2015

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. The success of our algorithm arises from derived bounds that suggest a new regularization penalty in terms of the Rademacher complexities of the corresponding families of kernel maps. In a series of experiments we demonstrate the improved performance of our algorithm as compared to baselines. Furthermore, the algorithm enjoys several favorable properties. The optimization problem is convex, it allows for learning with non-PDS kernels, and the solutions are highly sparse, resulting in improved classification speed and memory requirements.

cs.LG↗

arXiv2015

Non-parametric Revenue Optimization for Generalized Second Price Auctions

We present an extensive analysis of the key problem of learning optimal reserve prices for generalized second price auctions. We describe two algorithms for this task: one based on density estimation, and a novel algorithm benefiting from solid theoretical guarantees and with a very favorable running-time complexity of $O(n S \log (n S))$, where $n$ is the sample size and $S$ the number of slots. Our theoretical guarantees are more favorable than those previously presented in the literature. Additionally, we show that even if bidders do not play at an equilibrium, our second algorithm is still well defined and minimizes a quantity of interest. To our knowledge, this is the first attempt to apply learning algorithms to the problem of reserve price optimization in GSP auctions. Finally, we present the first convergence analysis of empirical equilibrium bidding functions to the unique symmetric Bayesian-Nash equilibrium of a GSP.

cs.LG↗

arXiv2015

Automata and Graph Compression

We present a theoretical framework for the compression of automata, which are widely used in speech processing and other natural language processing tasks. The framework extends to graph compression. Similar to stationary ergodic processes, we formulate a probabilistic process of graph and automata generation that captures real world phenomena and provide a universal compression scheme LZA for this probabilistic model. Further, we show that LZA significantly outperforms other compression techniques such as gzip and the UNIX compress command for several synthetic and real data sets.

cs.IT↗

arXiv2015

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. Unlike many previous algorithms for domain adaptation, our algorithm does not consist of a fixed reweighting of the losses over the training sample. We show that our algorithm benefits from a solid theoretical foundation and more favorable learning bounds than discrepancy minimization. We present a detailed description of our algorithm and give several efficient solutions for solving its optimization problem. We also report the results of several experiments showing that it outperforms discrepancy minimization.

cs.LG↗

arXiv2014

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. The choice of the reserve price is the main mechanism through which the auction revenue can be influenced in these electronic markets. We cast the problem of selecting the reserve price to optimize revenue as a learning problem and present a full theoretical analysis dealing with the complex properties of the corresponding loss function. We further give novel algorithms for solving this problem and report the results of several experiments in both synthetic and real data demonstrating their effectiveness.

cs.LG↗

arXiv2014

Revenue Optimization in Posted-Price Auctions with Strategic Buyers

We study revenue optimization learning algorithms for posted-price auctions with strategic buyers. We analyze a very broad family of monotone regret minimization algorithms for this problem, which includes the previously best known algorithm, and show that no algorithm in that family admits a strategic regret more favorable than $Ω(\sqrt{T})$. We then introduce a new algorithm that achieves a strategic regret differing from the lower bound only by a factor in $O(\log T)$, an exponential improvement upon the previous best algorithm. Our new algorithm admits a natural analysis and simpler proofs, and the ideas behind its design are general. We also report the results of empirical evaluations comparing our algorithm with the previous state of the art and show a consistent exponential improvement in several different scenarios.

cs.LG↗

arXiv2014

On the Disambiguation of Weighted Automata

We present a disambiguation algorithm for weighted automata. The algorithm admits two main stages: a pre-disambiguation stage followed by a transition removal stage. We give a detailed description of the algorithm and the proof of its correctness. The algorithm is not applicable to all weighted automata but we prove sufficient conditions for its applicability in the case of the tropical semiring by introducing the *weak twins property*. In particular, the algorithm can be used with all acyclic weighted automata, relevant to applications. While disambiguation can sometimes be achieved using determinization, our disambiguation algorithm in some cases can return a result that is exponentially smaller than any equivalent deterministic automaton. We also present some empirical evidence of the space benefits of disambiguation over determinization in speech recognition and machine translation applications.

cs.FL↗

arXiv2013

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. The inequality plays an important role in a variety of contexts, including the analysis of relative deviation bounds in learning theory and generalization bounds for unbounded loss functions.

cs.LG↗

arXiv2013

Perceptron Mistake Bounds

We present a brief survey of existing mistake bounds and introduce novel bounds for the Perceptron or the kernel Perceptron algorithm. Our novel bounds generalize beyond standard margin-loss type bounds, allow for any convex and Lipschitz loss function, and admit a very simple proof.

cs.LG↗

arXiv2012

New Analysis and Algorithm for Learning with Drifting Distributions

We present a new analysis of the problem of learning with drifting distributions in the batch setting using the notion of discrepancy. We prove learning bounds based on the Rademacher complexity of the hypothesis set and the discrepancy of distributions both for a drifting PAC scenario and a tracking scenario. Our bounds are always tighter and in some cases substantially improve upon previous ones based on the $L_1$ distance. We also present a generalization of the standard on-line to batch conversion to the drifting scenario in terms of the discrepancy and arbitrary convex combinations of hypotheses. We introduce a new algorithm exploiting these learning guarantees, which we show can be formulated as a simple QP. Finally, we report the results of preliminary experiments demonstrating the benefits of this algorithm.

cs.LG↗

arXiv2012

Multiple Source Adaptation and the Renyi Divergence

This paper presents a novel theoretical study of the general problem of multiple source adaptation using the notion of Renyi divergence. Our results build on our previous work [12], but significantly broaden the scope of that work in several directions. We extend previous multiple source loss guarantees based on distribution weighted combinations to arbitrary target distributions P, not necessarily mixtures of the source distributions, analyze both known and unknown target distribution cases, and prove a lower bound. We further extend our bounds to deal with the case where the learner receives an approximate distribution for each source instead of the exact one, and show that similar loss guarantees can be achieved depending on the divergence between the approximate and true distributions. We also analyze the case where the labeling functions of the source domains are somewhat different. Finally, we report the results of experiments with both an artificial data set and a sentiment analysis task, showing the performance benefits of the distribution weighted combinations and the quality of our bounds based on the Renyi divergence.

cs.LG↗

arXiv2012

L2 Regularization for Learning Kernels

The choice of the kernel is critical to the success of many learning algorithms but it is typically left to the user. Instead, the training data can be used to learn the kernel by selecting it out of a given family, such as that of non-negative linear combinations of p base kernels, constrained by a trace or L1 regularization. This paper studies the problem of learning kernels with the same family of kernels but with an L2 regularization instead, and for regression problems. We analyze the problem of learning kernels with ridge regression. We derive the form of the solution of the optimization problem and give an efficient iterative algorithm for computing that solution. We present a novel theoretical analysis of the problem based on stability and give learning bounds for orthogonal kernels that contain only an additive term O(pp/m) when compared to the standard kernel ridge regression stability bound. We also report the results of experiments indicating that L1 regularization can lead to modest improvements for a small number of kernels, but to performance degradations in larger-scale cases. In contrast, L2 regularization never degrades performance and in fact achieves significant improvements with a large number of kernels.

cs.LG↗

arXiv2012

Ensembles of Kernel Predictors

This paper examines the problem of learning with a finite and possibly large set of p base kernels. It presents a theoretical and empirical analysis of an approach addressing this problem based on ensembles of kernel predictors. This includes novel theoretical guarantees based on the Rademacher complexity of the corresponding hypothesis sets, the introduction and analysis of a learning algorithm based on these hypothesis sets, and a series of experiments using ensembles of kernel predictors with several data sets. Both convex combinations of kernel-based hypotheses and more general Lq-regularized nonnegative combinations are analyzed. These theoretical, algorithmic, and empirical results are compared with those achieved by using learning kernel techniques, which can be viewed as another approach for solving the same problem.

cs.LG↗

arXiv2010

On the Estimation of Coherence

Low-rank matrix approximations are often used to help scale standard machine learning algorithms to large-scale problems. Recently, matrix coherence has been used to characterize the ability to extract global information from a subset of matrix entries in the context of these low-rank approximations and other sampling-based algorithms, e.g., matrix com- pletion, robust PCA. Since coherence is defined in terms of the singular vectors of a matrix and is expensive to compute, the practical significance of these results largely hinges on the following question: Can we efficiently and accurately estimate the coherence of a matrix? In this paper we address this question. We propose a novel algorithm for estimating coherence from a small number of columns, formally analyze its behavior, and derive a new coherence-based matrix approximation bound based on this analysis. We then present extensive experimental results on synthetic and real datasets that corroborate our worst-case theoretical analysis, yet provide strong support for the use of our proposed algorithm whenever low-rank approximation is being considered. Our algorithm efficiently and accurately estimates matrix coherence across a wide range of datasets, and these coherence estimates are excellent predictors of the effectiveness of sampling-based matrix approximation on a case-by-case basis.

stat.ML↗

arXiv2009

New Generalization Bounds for Learning Kernels

This paper presents several novel generalization bounds for the problem of learning kernels based on the analysis of the Rademacher complexity of the corresponding hypothesis sets. Our bound for learning kernels with a convex combination of p base kernels has only a log(p) dependency on the number of kernels, p, which is considerably more favorable than the previous best bound given for the same problem. We also give a novel bound for learning with a linear combination of p base kernels with an L_2 regularization whose dependency on p is only in p^{1/4}.

cs.AI↗