arXiv subjects

Manfred K. Warmuth

Publications and source records attributed to Manfred K. Warmuth.

At least 37 records · Page 2Linked to original sources

arXiv2020

Reparameterizing Mirror Descent as Gradient Descent

Most of the recent successful applications of neural networks have been based on training with gradient descent updates. However, for some small networks, other mirror descent updates learn provably more efficiently when the target is sparse. We present a general framework for casting a mirror descent update as a gradient descent update on a different set of parameters. In some cases, the mirror descent reparameterization can be described as training a modified network with standard backpropagation. The reparameterization framework is versatile and covers a wide range of mirror descent updates, even cases where the domain is constrained. Our construction for the reparameterization argument is done for the continuous versions of the updates. Finding general criteria for the discrete versions to closely track their continuous counterparts remains an interesting open problem.

cs.LG↗

arXiv2020

Divergence-Based Motivation for Online EM and Combining Hidden Variable Models

Expectation-Maximization (EM) is a prominent approach for parameter estimation of hidden (aka latent) variable models. Given the full batch of data, EM forms an upper-bound of the negative log-likelihood of the model at each iteration and updates to the minimizer of this upper-bound. We first provide a "model level" interpretation of the EM upper-bound as sum of relative entropy divergences to a set of singleton models, induced by the set of observations. Our alternative motivation unifies the "observation level" and the "model level" view of the EM. As a result, we formulate an online version of the EM algorithm by adding an analogous inertia term which corresponds to the relative entropy divergence to the old model. Our motivation is more widely applicable than the previous approaches and leads to simple online updates for mixture of exponential distributions, hidden Markov models, and the first known online update for Kalman filters. Additionally, the finite sample form of the inertia term lets us derive online updates when there is no closed-form solution. Finally, we extend the analysis to the distributed setting where we motivate a systematic way of combining multiple hidden variable models. Experimentally, we validate the results on synthetic as well as real-world datasets.

cs.LG↗

arXiv2019

Robust Bi-Tempered Logistic Loss Based on Bregman Divergences

We introduce a temperature into the exponential function and replace the softmax output layer of neural nets by a high temperature generalization. Similarly, the logarithm in the log loss we use for training is replaced by a low temperature logarithm. By tuning the two temperatures we create loss functions that are non-convex already in the single layer case. When replacing the last layer of the neural nets by our bi-temperature generalization of logistic loss, the training becomes more robust to noise. We visualize the effect of tuning the two temperatures in a simple setting and show the efficacy of our method on large data sets. Our methodology is based on Bregman divergences and is superior to a related two-temperature method using the Tsallis divergence.

cs.LG↗

arXiv2019

An Implicit Form of Krasulina's k-PCA Update without the Orthonormality Constraint

We shed new insights on the two commonly used updates for the online $k$-PCA problem, namely, Krasulina's and Oja's updates. We show that Krasulina's update corresponds to a projected gradient descent step on the Stiefel manifold of the orthonormal $k$-frames, while Oja's update amounts to a gradient descent step using the unprojected gradient. Following these observations, we derive a more \emph{implicit} form of Krasulina's $k$-PCA update, i.e. a version that uses the information of the future gradient as much as possible. Most interestingly, our implicit Krasulina update avoids the costly QR-decomposition step by bypassing the orthonormality constraint. We show that the new update in fact corresponds to an online EM step applied to a probabilistic $k$-PCA model. The probabilistic view of the updates allows us to combine multiple models in a distributed setting. We show experimentally that the implicit Krasulina update yields superior convergence while being significantly faster. We also give strong evidence that the new update can benefit from parallelism and is more stable w.r.t. tuning of the learning rate.

cs.LG↗

arXiv2019

Two-temperature logistic regression based on the Tsallis divergence

We develop a variant of multiclass logistic regression that is significantly more robust to noise. The algorithm has one weight vector per class and the surrogate loss is a function of the linear activations (one per class). The surrogate loss of an example with linear activation vector $\mathbf{a}$ and class $c$ has the form $-\log_{t_1} \exp_{t_2} (a_c - G_{t_2}(\mathbf{a}))$ where the two temperatures $t_1$ and $t_2$ ''temper'' the $\log$ and $\exp$, respectively, and $G_{t_2}(\mathbf{a})$ is a scalar value that generalizes the log-partition function. We motivate this loss using the Tsallis divergence. Our method allows transitioning between non-convex and convex losses by the choice of the temperature parameters. As the temperature $t_1$ of the logarithm becomes smaller than the temperature $t_2$ of the exponential, the surrogate loss becomes ''quasi convex''. Various tunings of the temperatures recover previous methods and tuning the degree of non-convexity is crucial in the experiments. In particular, quasi-convexity and boundedness of the loss provide significant robustness to the outliers. We explain this by showing that $t_1 < 1$ caps the surrogate loss and $t_2 >1$ makes the predictive distribution have a heavy tail. We show that the surrogate loss is Bayes-consistent, even in the non-convex case. Additionally, we provide efficient iterative algorithms for calculating the log-partition value only in a few number of iterations. Our compelling experimental results on large real-world datasets show the advantage of using the two-temperature variant in the noisy as well as the noise free case.

cs.LG↗

arXiv2019

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. We present new online algorithms for path learning with non-additive count-based gains for the three settings of full information, semi-bandit and full bandit with very favorable regret guarantees. A key component of our algorithms is the definition and computation of an intermediate context-dependent automaton that enables us to use existing algorithms designed for additive gains. We further apply our methods to the important application of ensemble structured prediction. Finally, beyond count-based gains, we give an efficient implementation of the EXP3 algorithm for the full bandit setting with an arbitrary (non-additive) gain.

cs.LG↗

arXiv2019

Adaptive scale-invariant online algorithms for learning linear models

We consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function (comparator) in hindsight. Popular algorithms in this framework, such as Online Gradient Descent (OGD), have parameters (learning rates), which ideally should be tuned based on the scales of the features and the optimal comparator, but these quantities only become available at the end of the learning process. In this paper, we resolve the tuning problem by proposing online algorithms making predictions which are invariant under arbitrary rescaling of the features. The algorithms have no parameters to tune, do not require any prior knowledge on the scale of the instances or the comparator, and achieve regret bounds matching (up to a logarithmic factor) that of OGD with optimally tuned separate learning rates per dimension, while retaining comparable runtime performance.

cs.LG↗

arXiv2019

Minimax experimental design: Bridging the gap between statistical and worst-case approaches to least squares regression

In experimental design, we are given a large collection of vectors, each with a hidden response value that we assume derives from an underlying linear model, and we wish to pick a small subset of the vectors such that querying the corresponding responses will lead to a good estimator of the model. A classical approach in statistics is to assume the responses are linear, plus zero-mean i.i.d. Gaussian noise, in which case the goal is to provide an unbiased estimator with smallest mean squared error (A-optimal design). A related approach, more common in computer science, is to assume the responses are arbitrary but fixed, in which case the goal is to estimate the least squares solution using few responses, as quickly as possible, for worst-case inputs. Despite many attempts, characterizing the relationship between these two approaches has proven elusive. We address this by proposing a framework for experimental design where the responses are produced by an arbitrary unknown distribution. We show that there is an efficient randomized experimental design procedure that achieves strong variance bounds for an unbiased estimator using few responses in this general model. Nearly tight bounds for the classical A-optimality criterion, as well as improved bounds for worst-case responses, emerge as special cases of this result. In the process, we develop a new algorithm for a joint sampling distribution called volume sampling, and we propose a new i.i.d. importance sampling method: inverse score sampling. A key novelty of our analysis is in developing new expected error bounds for worst-case regression by controlling the tail behavior of i.i.d. sampling via the jointness of volume sampling. Our result motivates a new minimax-optimality criterion for experimental design which can be viewed as an extension of both A-optimal design and sampling for worst-case regression.

cs.LG↗

arXiv2018

Correcting the bias in least squares regression with volume-rescaled sampling

Consider linear regression where the examples are generated by an unknown distribution on $R^d\times R$. Without any assumptions on the noise, the linear least squares solution for any i.i.d. sample will typically be biased w.r.t. the least squares optimum over the entire distribution. However, we show that if an i.i.d. sample of any size k is augmented by a certain small additional sample, then the solution of the combined sample becomes unbiased. We show this when the additional sample consists of d points drawn jointly according to the input distribution that is rescaled by the squared volume spanned by the points. Furthermore, we propose algorithms to sample from this volume-rescaled distribution when the data distribution is only known through an i.i.d sample.

cs.LG↗

arXiv2018

Leveraged volume sampling for linear regression

Suppose an $n \times d$ design matrix in a linear regression problem is given, but the response for each point is hidden unless explicitly requested. The goal is to sample only a small number $k \ll n$ of the responses, and then produce a weight vector whose sum of squares loss over all points is at most $1+ε$ times the minimum. When $k$ is very small (e.g., $k=d$), jointly sampling diverse subsets of points is crucial. One such method called volume sampling has a unique and desirable property that the weight vector it produces is an unbiased estimate of the optimum. It is therefore natural to ask if this method offers the optimal unbiased estimate in terms of the number of responses $k$ needed to achieve a $1+ε$ loss approximation. Surprisingly we show that volume sampling can have poor behavior when we require a very accurate approximation -- indeed worse than some i.i.d. sampling techniques whose estimates are biased, such as leverage score sampling. We then develop a new rescaled variant of volume sampling that produces an unbiased estimate which avoids this bad behavior and has at least as good a tail bound as leverage score sampling: sample size $k=O(d\log d + d/ε)$ suffices to guarantee total loss at most $1+ε$ times the minimum with high probability. Thus, we improve on the best previously known sample size for an unbiased estimator, $k=O(d^2/ε)$. Our rescaling procedure leads to a new efficient algorithm for volume sampling which is based on a determinantal rejection sampling technique with potentially broader applications to determinantal point processes. Other contributions include introducing the combinatorics needed for rescaled volume sampling and developing tail bounds for sums of dependent random matrices which arise in the process.

cs.LG↗

arXiv2018

Reverse iterative volume sampling for linear regression

We study the following basic machine learning task: Given a fixed set of $d$-dimensional input points for a linear regression problem, we wish to predict a hidden response value for each of the points. We can only afford to attain the responses for a small subset of the points that are then used to construct linear predictions for all points in the dataset. The performance of the predictions is evaluated by the total square loss on all responses (the attained as well as the hidden ones). We show that a good approximate solution to this least squares problem can be obtained from just dimension $d$ many responses by using a joint sampling technique called volume sampling. Moreover, the least squares solution obtained for the volume sampled subproblem is an unbiased estimator of optimal solution based on all n responses. This unbiasedness is a desirable property that is not shared by other common subset selection techniques. Motivated by these basic properties, we develop a theoretical framework for studying volume sampling, resulting in a number of new matrix expectation equalities and statistical guarantees which are of importance not only to least squares regression but also to numerical linear algebra in general. Our methods also lead to a regularized variant of volume sampling, and we propose the first efficient algorithms for volume sampling which make this technique a practical tool in the machine learning toolbox. Finally, we provide experimental evidence which confirms our theoretical findings.

cs.LG↗

arXiv2018

Unbiased estimates for linear regression via volume sampling

Given a full rank matrix $X$ with more columns than rows, consider the task of estimating the pseudo inverse $X^+$ based on the pseudo inverse of a sampled subset of columns (of size at least the number of rows). We show that this is possible if the subset of columns is chosen proportional to the squared volume spanned by the rows of the chosen submatrix (ie, volume sampling). The resulting estimator is unbiased and surprisingly the covariance of the estimator also has a closed form: It equals a specific factor times $X^{+\top}X^+$. Pseudo inverse plays an important part in solving the linear least squares problem, where we try to predict a label for each column of $X$. We assume labels are expensive and we are only given the labels for the small subset of columns we sample from $X$. Using our methods we show that the weight vector of the solution for the sub problem is an unbiased estimator of the optimal solution for the whole problem based on all column labels. We believe that these new formulas establish a fundamental connection between linear least squares and volume sampling. We use our methods to obtain an algorithm for volume sampling that is faster than state-of-the-art and for obtaining bounds for the total loss of the estimated least-squares solution on all labeled columns.

cs.LG↗

arXiv2018

A more globally accurate dimensionality reduction method using triplets

We first show that the commonly used dimensionality reduction (DR) methods such as t-SNE and LargeVis poorly capture the global structure of the data in the low dimensional embedding. We show this via a number of tests for the DR methods that can be easily applied by any practitioner to the dataset at hand. Surprisingly enough, t-SNE performs the best w.r.t. the commonly used measures that reward the local neighborhood accuracy such as precision-recall while having the worst performance in our tests for global structure. We then contrast the performance of these two DR method against our new method called TriMap. The main idea behind TriMap is to capture higher orders of structure with triplet information (instead of pairwise information used by t-SNE and LargeVis), and to minimize a robust loss function for satisfying the chosen triplets. We provide compelling experimental evidence on large natural datasets for the clear advantage of the TriMap DR results. As LargeVis, TriMap scales linearly with the number of data points.

cs.LG↗

arXiv2018

Subsampling for Ridge Regression via Regularized Volume Sampling

Given $n$ vectors $\mathbf{x}_i\in \mathbb{R}^d$, we want to fit a linear regression model for noisy labels $y_i\in\mathbb{R}$. The ridge estimator is a classical solution to this problem. However, when labels are expensive, we are forced to select only a small subset of vectors $\mathbf{x}_i$ for which we obtain the labels $y_i$. We propose a new procedure for selecting the subset of vectors, such that the ridge estimator obtained from that subset offers strong statistical guarantees in terms of the mean squared prediction error over the entire dataset of $n$ labeled vectors. The number of labels needed is proportional to the statistical dimension of the problem which is often much smaller than $d$. Our method is an extension of a joint subsampling procedure called volume sampling. A second major contribution is that we speed up volume sampling so that it is essentially as efficient as leverage scores, which is the main i.i.d. subsampling procedure for this task. Finally, we show theoretically and experimentally that volume sampling has a clear advantage over any i.i.d. sampling when labels are expensive.

cs.LG↗

arXiv2017

Low-dimensional Data Embedding via Robust Ranking

We describe a new method called t-ETE for finding a low-dimensional embedding of a set of objects in Euclidean space. We formulate the embedding problem as a joint ranking problem over a set of triplets, where each triplet captures the relative similarities between three objects in the set. By exploiting recent advances in robust ranking, t-ETE produces high-quality embeddings even in the presence of a significant amount of noise and better preserves local scale than known methods, such as t-STE and t-SNE. In particular, our method produces significantly better results than t-SNE on signature datasets while also being faster to compute.

cs.AI↗

arXiv2016

Labeled compression schemes for extremal classes

It is a long-standing open problem whether there always exists a compression scheme whose size is of the order of the Vapnik-Chervonienkis (VC) dimension $d$. Recently compression schemes of size exponential in $d$ have been found for any concept class of VC dimension $d$. Previously, compression schemes of size $d$ have been given for maximum classes, which are special concept classes whose size equals an upper bound due to Sauer-Shelah. We consider a generalization of maximum classes called extremal classes. Their definition is based on a powerful generalization of the Sauer-Shelah bound called the Sandwich Theorem, which has been studied in several areas of combinatorics and computer science. The key result of the paper is a construction of a sample compression scheme for extremal classes of size equal to their VC dimension. We also give a number of open problems concerning the combinatorial structure of extremal classes and the existence of unlabeled compression schemes for them.

cs.LG↗

arXiv2015

PCA with Gaussian perturbations

Most of machine learning deals with vector parameters. Ideally we would like to take higher order information into account and make use of matrix or even tensor parameters. However the resulting algorithms are usually inefficient. Here we address on-line learning with matrix parameters. It is often easy to obtain online algorithm with good generalization performance if you eigendecompose the current parameter matrix in each trial (at a cost of $O(n^3)$ per trial). Ideally we want to avoid the decompositions and spend $O(n^2)$ per trial, i.e. linear time in the size of the matrix data. There is a core trade-off between the running time and the generalization performance, here measured by the regret of the on-line algorithm (total gain of the best off-line predictor minus the total gain of the on-line algorithm). We focus on the key matrix problem of rank $k$ Principal Component Analysis in $\mathbb{R}^n$ where $k \ll n$. There are $O(n^3)$ algorithms that achieve the optimum regret but require eigendecompositions. We develop a simple algorithm that needs $O(kn^2)$ per trial whose regret is off by a small factor of $O(n^{1/4})$. The algorithm is based on the Follow the Perturbed Leader paradigm. It replaces full eigendecompositions at each trial by the problem finding $k$ principal components of the current covariance matrix that is perturbed by Gaussian noise.

cs.LG↗

arXiv2014

A Bayesian Probability Calculus for Density Matrices

One of the main concepts in quantum physics is a density matrix, which is a symmetric positive definite matrix of trace one. Finite probability distributions are a special case where the density matrix is restricted to be diagonal. Density matrices are mixtures of dyads, where a dyad has the form uu' for any any unit column vector u. These unit vectors are the elementary events of the generalized probability space. Perhaps the simplest case to see that something unusual is going on is the case of uniform density matrix, i.e. 1/n times identity. This matrix assigns probability 1/n to every unit vector, but of course there are infinitely many of them. The new normalization rule thus says that sum of probabilities over any orthonormal basis of directions is one. We develop a probability calculus based on these more general distributions that includes definitions of joints, conditionals and formulas that relate these, i.e. analogs of the theorem of total probability, various Bayes rules for the calculation of posterior density matrices, etc. The resulting calculus parallels the familiar 'classical' probability calculus and always retains the latter as a special case when all matrices are diagonal. Whereas the classical Bayesian methods maintain uncertainty about which model is 'best', the generalization maintains uncertainty about which unit direction has the largest variance. Surprisingly the bounds also generalize: as in the classical setting we bound the negative log likelihood of the data by the negative log likelihood of the MAP estimator.

quant-ph↗