Searcharxiv⌕ Search

arXiv subjects

Nisheeth K. Vishnoi

Publications and source records attributed to Nisheeth K. Vishnoi.

At least 73 records · Page 4Linked to original sources
arXiv2018

Convex Optimization with Unbounded Nonconvex Oracles using Simulated Annealing

We consider the problem of minimizing a convex objective function $F$ when one can only evaluate its noisy approximation $\hat{F}$. Unless one assumes some structure on the noise, $\hat{F}$ may be an arbitrary nonconvex function, making the task of minimizing $F$ intractable. To overcome this, prior work has often focused on the case when $F(x)-\hat{F}(x)$ is uniformly-bounded. In this paper we study the more general case when the noise has magnitude $αF(x) + β$ for some $α, β> 0$, and present a polynomial time algorithm that finds an approximate minimizer of $F$ for this noise model. Previously, Markov chains, such as the stochastic gradient Langevin dynamics, have been used to arrive at approximate solutions to these optimization problems. However, for the noise model considered in this paper, no single temperature allows such a Markov chain to both mix quickly and concentrate near the global minimizer. We bypass this by combining "simulated annealing" with the stochastic gradient Langevin dynamics, and gradually decreasing the temperature of the chain in order to approach the global minimizer. As a corollary one can approximately minimize a nonconvex function that is close to a convex function; however, the closeness can deteriorate as one moves away from the optimum.

cs.DS↗
arXiv2018

Geodesic Convex Optimization: Differentiation on Manifolds, Geodesics, and Convexity

Convex optimization is a vibrant and successful area due to the existence of a variety of efficient algorithms that leverage the rich structure provided by convexity. Convexity of a smooth set or a function in a Euclidean space is defined by how it interacts with the standard differential structure in this space -- the Hessian of a convex function has to be positive semi-definite everywhere. However, in recent years, there is a growing demand to understand non-convexity and develop computational methods to optimize non-convex functions. Intriguingly, there is a type of non-convexity that disappears once one introduces a suitable differentiable structure and redefines convexity with respect to the straight lines, or {\em geodesics}, with respect to this structure. Such convexity is referred to as {\em geodesic convexity}. Interest in studying it arises due to recent reformulations of some non-convex problems as geodesically convex optimization problems over geodesically convex sets. Geodesics on manifolds have been extensively studied in various branches of Mathematics and Physics. However, unlike convex optimization, understanding geodesics and geodesic convexity from a computational point of view largely remains a mystery. The goal of this exposition is to introduce the first part of geodesic convex optimization -- geodesic convexity -- in a self-contained manner. We first present a variety of notions from differential and Riemannian geometry such as differentiation on manifolds, geodesics, and then introduce geodesic convexity. We conclude by showing that certain non-convex optimization problems such as computing the Brascamp-Lieb constant and the operator scaling problem have geodesically convex formulations.

math.OC↗
arXiv2018

Isolating a Vertex via Lattices: Polytopes with Totally Unimodular Faces

We present a geometric approach towards derandomizing the Isolation Lemma by Mulmuley, Vazirani, and Vazirani. In particular, our approach produces a quasi-polynomial family of weights, where each weight is an integer and quasi-polynomially bounded, that can isolate a vertex in any 0/1 polytope for which each face lies in an affine space defined by a totally unimodular matrix. This includes the polytopes given by totally unimodular constraints and generalizes the recent derandomization of the Isolation Lemma for bipartite perfect matching and matroid intersection. We prove our result by associating a lattice to each face of the polytope and showing that if there is a totally unimodular kernel matrix for this lattice, then the number of vectors of length within 3/2 of the shortest vector in it is polynomially bounded. The proof of this latter geometric fact is combinatorial and follows from a polynomial bound on the number of circuits of size within 3/2 of the shortest circuit in a regular matroid. This is the technical core of the paper and relies on a variant of Seymour's decomposition theorem for regular matroids. It generalizes an influential result by Karger on the number of minimum cuts in a graph to regular matroids.

cs.DS↗
arXiv2018

On Geodesically Convex Formulations for the Brascamp-Lieb Constant

We consider two non-convex formulations for computing the optimal constant in the Brascamp-Lieb inequality corresponding to a given datum, and show that they are geodesically log-concave on the manifold of positive definite matrices endowed with the Riemannian metric corresponding to the Hessian of the log-determinant function. The first formulation is present in the work of Lieb and the second is inspired by the work of Bennett et al. Recent works of Garg et al.and Allen-Zhu et al. also imply a geodesically log-concave formulation of the Brascamp-Lieb constant through a reduction to the operator scaling problem. However, the dimension of the arising optimization problem in their reduction depends exponentially on the number of bits needed to describe the Brascamp-Lieb datum. The formulations presented here have dimensions that are polynomial in the bit complexity of the input datum.

cs.DS↗
arXiv2018

An Algorithmic Framework to Control Bias in Bandit-based Personalization

Personalization is pervasive in the online space as it leads to higher efficiency and revenue by allowing the most relevant content to be served to each user. However, recent studies suggest that personalization methods can propagate societal or systemic biases and polarize opinions; this has led to calls for regulatory mechanisms and algorithms to combat bias and inequality. Algorithmically, bandit optimization has enjoyed great success in learning user preferences and personalizing content or feeds accordingly. We propose an algorithmic framework that allows for the possibility to control bias or discrimination in such bandit-based personalization. Our model allows for the specification of general fairness constraints on the sensitive types of the content that can be displayed to a user. The challenge, however, is to come up with a scalable and low regret algorithm for the constrained optimization problem that arises. Our main technical contribution is a provably fast and low-regret algorithm for the fairness-constrained bandit optimization problem. Our proofs crucially leverage the special structure of our problem. Experiments on synthetic and real-world data sets show that our algorithmic framework can control bias with only a minor loss to revenue.

cs.LG↗
arXiv2018

Fair and Diverse DPP-based Data Summarization

Sampling methods that choose a subset of the data proportional to its diversity in the feature space are popular for data summarization. However, recent studies have noted the occurrence of bias (under- or over-representation of a certain gender or race) in such data summarization methods. In this paper we initiate a study of the problem of outputting a diverse and fair summary of a given dataset. We work with a well-studied determinantal measure of diversity and corresponding distributions (DPPs) and present a framework that allows us to incorporate a general class of fairness constraints into such distributions. Coming up with efficient algorithms to sample from these constrained determinantal distributions, however, suffers from a complexity barrier and we present a fast sampler that is provably good when the input vectors satisfy a natural property. Our experimental results on a real-world and an image dataset show that the diversity of the samples produced by adding fairness constraints is not too far from the unconstrained case, and we also provide a theoretical explanation of it.

cs.LG↗
arXiv2017

Belief Propagation, Bethe Approximation and Polynomials

Factor graphs are important models for succinctly representing probability distributions in machine learning, coding theory, and statistical physics. Several computational problems, such as computing marginals and partition functions, arise naturally when working with factor graphs. Belief propagation is a widely deployed iterative method for solving these problems. However, despite its significant empirical success, not much is known about the correctness and efficiency of belief propagation. Bethe approximation is an optimization-based framework for approximating partition functions. While it is known that the stationary points of the Bethe approximation coincide with the fixed points of belief propagation, in general, the relation between the Bethe approximation and the partition function is not well understood. It has been observed that for a few classes of factor graphs, the Bethe approximation always gives a lower bound to the partition function, which distinguishes them from the general case, where neither a lower bound, nor an upper bound holds universally. This has been rigorously proved for permanents and for attractive graphical models. Here we consider bipartite normal factor graphs and show that if the local constraints satisfy a certain analytic property, the Bethe approximation is a lower bound to the partition function. We arrive at this result by viewing factor graphs through the lens of polynomials. In this process, we reformulate the Bethe approximation as a polynomial optimization problem. Our sufficient condition for the lower bound property to hold is inspired by recent developments in the theory of real stable polynomials. We believe that this way of viewing factor graphs and its connection to real stability might lead to a better understanding of belief propagation and factor graphs in general.

cs.LG↗
arXiv2017

Fair Personalization

Personalization is pervasive in the online space as, when combined with learning, it leads to higher efficiency and revenue by allowing the most relevant content to be served to each user. However, recent studies suggest that such personalization can propagate societal or systemic biases, which has led to calls for regulatory mechanisms and algorithms to combat inequality. Here we propose a rigorous algorithmic framework that allows for the possibility to control biased or discriminatory personalization with respect to sensitive attributes of users without losing all of the benefits of personalization.

cs.CY↗
arXiv2017

A Distributed Learning Dynamics in Social Groups

We study a distributed learning process observed in human groups and other social animals. This learning process appears in settings in which each individual in a group is trying to decide over time, in a distributed manner, which option to select among a shared set of options. Specifically, we consider a stochastic dynamics in a group in which every individual selects an option in the following two-step process: (1) select a random individual and observe the option that individual chose in the previous time step, and (2) adopt that option if its stochastic quality was good at that time step. Various instantiations of such distributed learning appear in nature, and have also been studied in the social science literature. From the perspective of an individual, an attractive feature of this learning process is that it is a simple heuristic that requires extremely limited computational capacities. But what does it mean for the group -- could such a simple, distributed and essentially memoryless process lead the group as a whole to perform optimally? We show that the answer to this question is yes -- this distributed learning is highly effective at identifying the best option and is close to optimal for the group overall. Our analysis also gives quantitative bounds that show fast convergence of these stochastic dynamics. Prior to our work the only theoretical work related to such learning dynamics has been either in deterministic special cases or in the asymptotic setting. Finally, we observe that our infinite population dynamics is a stochastic variant of the classic multiplicative weights update (MWU) method. Consequently, we arrive at the following interesting converse: the learning dynamics on a finite population considered here can be viewed as a novel distributed and low-memory implementation of the classic MWU method.

cs.LG↗
arXiv2017

On the Complexity of Constrained Determinantal Point Processes

Determinantal Point Processes (DPPs) are probabilistic models that arise in quantum physics and random matrix theory and have recently found numerous applications in computer science. DPPs define distributions over subsets of a given ground set, they exhibit interesting properties such as negative correlation, and, unlike other models, have efficient algorithms for sampling. When applied to kernel methods in machine learning, DPPs favor subsets of the given data with more diverse features. However, many real-world applications require efficient algorithms to sample from DPPs with additional constraints on the subset, e.g., partition or matroid constraints that are important to ensure priors, resource or fairness constraints on the sampled subset. Whether one can efficiently sample from DPPs in such constrained settings is an important problem that was first raised in a survey of DPPs by \cite{KuleszaTaskar12} and studied in some recent works in the machine learning literature. The main contribution of our paper is the first resolution of the complexity of sampling from DPPs with constraints. We give exact efficient algorithms for sampling from constrained DPPs when their description is in unary. Furthermore, we prove that when the constraints are specified in binary, this problem is #P-hard via a reduction from the problem of computing mixed discriminants implying that it may be unlikely that there is an FPRAS. Our results benefit from viewing the constrained sampling problem via the lens of polynomials. Consequently, we obtain a few algorithms of independent interest: 1) to count over the base polytope of regular matroids when there are additional (succinct) budget constraints and, 2) to evaluate and compute the mixed characteristic polynomials, that played a central role in the resolution of the Kadison-Singer problem, for certain special cases.

cs.DS↗
arXiv2017

On Convex Programming Relaxations for the Permanent

In recent years, several convex programming relaxations have been proposed to estimate the permanent of a non-negative matrix, notably in the works of Gurvits and Samorodnitsky. However, the origins of these relaxations and their relationships to each other have remained somewhat mysterious. We present a conceptual framework, implicit in the belief propagation literature, to systematically arrive at these convex programming relaxations for estimating the permanent -- as approximations to an exponential-sized max-entropy convex program for computing the permanent. Further, using standard convex programming techniques such as duality, we establish equivalence of these aforementioned relaxations to those based on capacity-like quantities studied by Gurvits and Anari et al.

cs.DS↗
arXiv2016

Real Stable Polynomials and Matroids: Optimization and Counting

A great variety of fundamental optimization and counting problems arising in computer science, mathematics and physics can be reduced to one of the following computational tasks involving polynomials and set systems: given an $m$-variate real polynomial $g$ and a family of subsets $B$ of $[m]$, (1) find $S\in B$ such that the monomial in $g$ corresponding to $S$ has the largest coefficient in $g$, or (2) compute the sum of coefficients of monomials in $g$ corresponding to all the sets in $B$. Special cases of these problems, such as computing permanents, sampling from DPPs and maximizing subdeterminants have been topics of recent interest in theoretical computer science. In this paper we present a general convex programming framework geared to solve both of these problems. We show that roughly, when $g$ is a real stable polynomial with non-negative coefficients and $B$ is a matroid, the integrality gap of our relaxation is finite and depends only on $m$ (and not on the coefficients of g). Prior to our work, such results were known only in sporadic cases that relied on the structure of $g$ and $B$; it was not even clear if one could formulate a convex relaxation that has a finite integrality gap beyond these special cases. Two notable examples are a result by Gurvits on the van der Waerden conjecture for real stable $g$ when $B$ is a single element and a result by Nikolov and Singh for multilinear real stable polynomials when $B$ is a partition matroid. Our work, which encapsulates most interesting cases of $g$ and $B$, benefits from both - we were inspired by the latter in deriving the right convex programming relaxation and the former in establishing the integrality gap. However, proving our results requires significant extensions of both; in that process we come up with new notions and connections between stable polynomials and matroids which should be of independent interest.

cs.DS↗
arXiv2016

How to be Fair and Diverse?

Due to the recent cases of algorithmic bias in data-driven decision-making, machine learning methods are being put under the microscope in order to understand the root cause of these biases and how to correct them. Here, we consider a basic algorithmic task that is central in machine learning: subsampling from a large data set. Subsamples are used both as an end-goal in data summarization (where fairness could either be a legal, political or moral requirement) and to train algorithms (where biases in the samples are often a source of bias in the resulting model). Consequently, there is a growing effort to modify either the subsampling methods or the algorithms themselves in order to ensure fairness. However, in doing so, a question that seems to be overlooked is whether it is possible to produce fair subsamples that are also adequately representative of the feature space of the data set - an important and classic requirement in machine learning. Can diversity and fairness be simultaneously ensured? We start by noting that, in some applications, guaranteeing one does not necessarily guarantee the other, and a new approach is required. Subsequently, we present an algorithmic framework which allows us to produce both fair and diverse samples. Our experimental results on an image summarization task show marked improvements in fairness without compromising feature diversity by much, giving us the best of both the worlds.

cs.LG↗
arXiv2016

Matrix Inversion Is As Easy As Exponentiation

We prove that the inverse of a positive-definite matrix can be approximated by a weighted-sum of a small number of matrix exponentials. Combining this with a previous result [OSV12], we establish an equivalence between matrix inversion and exponentiation up to polylogarithmic factors. In particular, this connection justifies the use of Laplacian solvers for designing fast semi-definite programming based algorithms for certain graph problems. The proof relies on the Euler-Maclaurin formula and certain bounds derived from the Riemann zeta function.

cs.DS↗
arXiv2016

The Mixing Time of the Dikin Walk in a Polytope - A Simple Proof

We study the mixing time of the Dikin walk in a polytope - a random walk based on the log-barrier from the interior point method literature. This walk, and a close variant, were studied by Narayanan (2016) and Kannan-Narayanan (2012). Bounds on its mixing time are important for algorithms for sampling and optimization over polytopes. Here, we provide a simple proof of their result that this random walk mixes in time O(mn) for an n-dimensional polytope described using m inequalities.

cs.DS↗
arXiv2016

IRLS and Slime Mold: Equivalence and Convergence

In this paper we present a connection between two dynamical systems arising in entirely different contexts: one in signal processing and the other in biology. The first is the famous Iteratively Reweighted Least Squares (IRLS) algorithm used in compressed sensing and sparse recovery while the second is the dynamics of a slime mold (Physarum polycephalum). Both of these dynamics are geared towards finding a minimum l1-norm solution in an affine subspace. Despite its simplicity the convergence of the IRLS method has been shown only for a certain regularization of it and remains an important open problem. Our first result shows that the two dynamics are projections of the same dynamical system in higher dimensions. As a consequence, and building on the recent work on Physarum dynamics, we are able to prove convergence and obtain complexity bounds for a damped version of the IRLS algorithm.

cs.DS↗
arXiv2015

On the Computational Complexity of Limit Cycles in Dynamical Systems

We study the Poincare-Bendixson theorem for two-dimensional continuous dynamical systems in compact domains from the point of view of computation, seeking algorithms for finding the limit cycle promised by this classical result. We start by considering a discrete analogue of this theorem and show that both finding a point on a limit cycle, and determining if a given point is on one, are PSPACE-complete. For the continuous version, we show that both problems are uncomputable in the real complexity sense; i.e., their complexity is arbitrarily high. Subsequently, we introduce a notion of an "approximate cycle" and prove an "approximate" Poincaré-Bendixson theorem guaranteeing that some orbits come very close to forming a cycle in the absence of approximate fixpoints; surprisingly, it holds for all dimensions. The corresponding computational problem defined in terms of arithmetic circuits is PSPACE-complete.

cs.CC↗