arXiv subjects

Yash Deshpande

Publications and source records attributed to Yash Deshpande.

32 records · Page 2Linked to original sources

arXiv2021

VisualSem: A High-quality Knowledge Graph for Vision and Language

An exciting frontier in natural language understanding (NLU) and generation (NLG) calls for (vision-and-) language models that can efficiently access external structured knowledge repositories. However, many existing knowledge bases only cover limited domains, or suffer from noisy data, and most of all are typically hard to integrate into neural language pipelines. To fill this gap, we release VisualSem: a high-quality knowledge graph (KG) which includes nodes with multilingual glosses, multiple illustrative images, and visually relevant relations. We also release a neural multi-modal retrieval model that can use images or sentences as inputs and retrieves entities in the KG. This multi-modal retrieval model can be integrated into any (neural network) model pipeline. We encourage the research community to use VisualSem for data augmentation and/or as a source of grounding, among other possible uses. VisualSem as well as the multi-modal retrieval models are publicly available and can be downloaded in this URL: https://github.com/iacercalixto/visualsem

cs.CL↗

arXiv2021

Analysis of Tree-Algorithms with Multi-Packet Reception

In this paper, we analyze binary-tree algorithms in a setup in which the receiver can perform multi-packet reception (MPR) of up to and including K packets simultaneously. The analysis addresses both traffic-independent performance as well as performance under Poisson arrivals. For the former case, we show that the throughput, when normalized with respect to the assumed linear increase in resources required to achieve K-MPR capability, tends to the same value that holds for the single-reception setup. However, when coupled with Poisson arrivals in the windowed access scheme, the normalized throughput increases with K, and we present evidence that it asymptotically tends to 1. We also provide performance results for the modified tree algorithm with K-MPR in the clipped access scheme. To the best of our knowledge, this is the first paper that provides an analytical treatment and a number of fundamental insights in the performance of tree-algorithms with MPR.

cs.NI↗

arXiv2020

Online Debiasing for Adaptively Collected High-dimensional Data with Applications to Time Series Analysis

Adaptive collection of data is commonplace in applications throughout science and engineering. From the point of view of statistical inference however, adaptive data collection induces memory and correlation in the samples, and poses significant challenge. We consider the high-dimensional linear regression, where the samples are collected adaptively, and the sample size $n$ can be smaller than $p$, the number of covariates. In this setting, there are two distinct sources of bias: the first due to regularization imposed for consistent estimation, e.g. using the LASSO, and the second due to adaptivity in collecting the samples. We propose "online debiasing", a general procedure for estimators such as the LASSO, which addresses both sources of bias. In two concrete contexts $(i)$ time series analysis and $(ii)$ batched data collection, we demonstrate that online debiasing optimally debiases the LASSO estimate when the underlying parameter $θ_0$ has sparsity of order $o(\sqrt{n}/\log p)$. In this regime, the debiased estimator can be used to compute $p$-values and confidence intervals of optimal size.

stat.ME↗

arXiv2020

Accurate Inference for Adaptive Linear Models

Estimators computed from adaptively collected data do not behave like their non-adaptive brethren. Rather, the sequential dependence of the collection policy can lead to severe distributional biases that persist even in the infinite data limit. We develop a general method -- $\mathbf{W}$-decorrelation -- for transforming the bias of adaptive linear regression estimators into variance. The method uses only coarse-grained information about the data collection policy and does not need access to propensity scores or exact knowledge of the policy. We bound the finite-sample bias and variance of the $\mathbf{W}$-estimator and develop asymptotically correct confidence intervals based on a novel martingale central limit theorem. We then demonstrate the empirical benefits of the generic $\mathbf{W}$-decorrelation procedure in two different adaptive data settings: the multi-armed bandit and the autoregressive time series.

stat.ML↗

arXiv2018

Contextual Stochastic Block Models

We provide the first information theoretic tight analysis for inference of latent community structure given a sparse graph along with high dimensional node covariates, correlated with the same latent communities. Our work bridges recent theoretical breakthroughs in the detection of latent community structure without nodes covariates and a large body of empirical work using diverse heuristics for combining node covariates with graphs for inference. The tightness of our analysis implies in particular, the information theoretical necessity of combining the different sources of information. Our analysis holds for networks of large degrees as well as for a Gaussian version of the model.

cs.SI↗

arXiv2018

The threshold for SDP-refutation of random regular NAE-3SAT

Unlike its cousin 3SAT, the NAE-3SAT (not-all-equal-3SAT) problem has the property that spectral/SDP algorithms can efficiently refute random instances when the constraint density is a large constant (with high probability). But do these methods work immediately above the "satisfiability threshold", or is there still a range of constraint densities for which random NAE-3SAT instances are unsatisfiable but hard to refute? We show that the latter situation prevails, at least in the context of random regular instances and SDP-based refutation. More precisely, whereas a random $d$-regular instance of NAE-3SAT is easily shown to be unsatisfiable (whp) once $d \geq 8$, we establish the following sharp threshold result regarding efficient refutation: If $d < 13.5$ then the basic SDP, even augmented with triangle inequalities, fails to refute satisfiability (whp), if $d > 13.5$ then even the most basic spectral algorithm refutes satisfiability~(whp).

cs.DS↗

arXiv2017

Inference in Graphical Models via Semidefinite Programming Hierarchies

Maximum A posteriori Probability (MAP) inference in graphical models amounts to solving a graph-structured combinatorial optimization problem. Popular inference algorithms such as belief propagation (BP) and generalized belief propagation (GBP) are intimately related to linear programming (LP) relaxation within the Sherali-Adams hierarchy. Despite the popularity of these algorithms, it is well understood that the Sum-of-Squares (SOS) hierarchy based on semidefinite programming (SDP) can provide superior guarantees. Unfortunately, SOS relaxations for a graph with $n$ vertices require solving an SDP with $n^{Θ(d)}$ variables where $d$ is the degree in the hierarchy. In practice, for $d\ge 4$, this approach does not scale beyond a few tens of variables. In this paper, we propose binary SDP relaxations for MAP inference using the SOS hierarchy with two innovations focused on computational efficiency. Firstly, in analogy to BP and its variants, we only introduce decision variables corresponding to contiguous regions in the graphical model. Secondly, we solve the resulting SDP using a non-convex Burer-Monteiro style method, and develop a sequential rounding procedure. We demonstrate that the resulting algorithm can solve problems with tens of thousands of variables within minutes, and outperforms BP and GBP on practical problems such as image denoising and Ising spin glasses. Finally, for specific graph types, we establish a sufficient condition for the tightness of the proposed partial SOS relaxation.

stat.ML↗

arXiv2016

Sparse PCA via Covariance Thresholding

In sparse principal component analysis we are given noisy observations of a low-rank matrix of dimension $n\times p$ and seek to reconstruct it under additional sparsity assumptions. In particular, we assume here each of the principal components $\mathbf{v}_1,\dots,\mathbf{v}_r$ has at most $s_0$ non-zero entries. We are particularly interested in the high dimensional regime wherein $p$ is comparable to, or even much larger than $n$. In an influential paper, \cite{johnstone2004sparse} introduced a simple algorithm that estimates the support of the principal vectors $\mathbf{v}_1,\dots,\mathbf{v}_r$ by the largest entries in the diagonal of the empirical covariance. This method can be shown to identify the correct support with high probability if $s_0\le K_1\sqrt{n/\log p}$, and to fail with high probability if $s_0\ge K_2 \sqrt{n/\log p}$ for two constants $0<K_1,K_2<\infty$. Despite a considerable amount of work over the last ten years, no practical algorithm exists with provably better support recovery guarantees. Here we analyze a covariance thresholding algorithm that was recently proposed by \cite{KrauthgamerSPCA}. On the basis of numerical simulations (for the rank-one case), these authors conjectured that covariance thresholding correctly recover the support with high probability for $s_0\le K\sqrt{n}$ (assuming $n$ of the same order as $p$). We prove this conjecture, and in fact establish a more general guarantee including higher-rank as well as $n$ much smaller than $p$. Recent lower bounds \cite{berthet2013computational, ma2015sum} suggest that no polynomial time algorithm can do significantly better. The key technical component of our analysis develops new bounds on the norm of kernel random matrices, in regimes that were not considered before.

math.ST↗

arXiv2015

Asymptotic Mutual Information for the Two-Groups Stochastic Block Model

We develop an information-theoretic view of the stochastic block model, a popular statistical model for the large-scale structure of complex networks. A graph $G$ from such a model is generated by first assigning vertex labels at random from a finite alphabet, and then connecting vertices with edge probabilities depending on the labels of the endpoints. In the case of the symmetric two-group model, we establish an explicit `single-letter' characterization of the per-vertex mutual information between the vertex labels and the graph. The explicit expression of the mutual information is intimately related to estimation-theoretic quantities, and --in particular-- reveals a phase transition at the critical point for community detection. Below the critical point the per-vertex mutual information is asymptotically the same as if edges were independent. Correspondingly, no algorithm can estimate the partition better than random guessing. Conversely, above the threshold, the per-vertex mutual information is strictly smaller than the independent-edges upper bound. In this regime there exists a procedure that estimates the vertex labels better than random guessing.

cs.IT↗

arXiv2015

Improved Sum-of-Squares Lower Bounds for Hidden Clique and Hidden Submatrix Problems

Given a large data matrix $A\in\mathbb{R}^{n\times n}$, we consider the problem of determining whether its entries are i.i.d. with some known marginal distribution $A_{ij}\sim P_0$, or instead $A$ contains a principal submatrix $A_{{\sf Q},{\sf Q}}$ whose entries have marginal distribution $A_{ij}\sim P_1\neq P_0$. As a special case, the hidden (or planted) clique problem requires to find a planted clique in an otherwise uniformly random graph. Assuming unbounded computational resources, this hypothesis testing problem is statistically solvable provided $|{\sf Q}|\ge C \log n$ for a suitable constant $C$. However, despite substantial effort, no polynomial time algorithm is known that succeeds with high probability when $|{\sf Q}| = o(\sqrt{n})$. Recently Meka and Wigderson \cite{meka2013association}, proposed a method to establish lower bounds within the Sum of Squares (SOS) semidefinite hierarchy. Here we consider the degree-$4$ SOS relaxation, and study the construction of \cite{meka2013association} to prove that SOS fails unless $k\ge C\, n^{1/3}/\log n$. An argument presented by Barak implies that this lower bound cannot be substantially improved unless the witness construction is changed in the proof. Our proof uses the moments method to bound the spectrum of a certain random association scheme, i.e. a symmetric random matrix whose rows and columns are indexed by the edges of an Erdös-Renyi random graph.

cs.CC↗

arXiv2014

Information-theoretically Optimal Sparse PCA

Sparse Principal Component Analysis (PCA) is a dimensionality reduction technique wherein one seeks a low-rank representation of a data matrix with additional sparsity constraints on the obtained representation. We consider two probabilistic formulations of sparse PCA: a spiked Wigner and spiked Wishart (or spiked covariance) model. We analyze an Approximate Message Passing (AMP) algorithm to estimate the underlying signal and show, in the high dimensional limit, that the AMP estimates are information-theoretically optimal. As an immediate corollary, our results demonstrate that the posterior expectation of the underlying signal, which is often intractable to compute, can be obtained using a polynomial-time scheme. Our results also effectively provide a single-letter characterization of the sparse PCA problem.

cs.IT↗

arXiv2013

Finding Hidden Cliques of Size \sqrt{N/e} in Nearly Linear Time

Consider an Erdös-Renyi random graph in which each edge is present independently with probability 1/2, except for a subset $\sC_N$ of the vertices that form a clique (a completely connected subgraph). We consider the problem of identifying the clique, given a realization of such a random graph. The best known algorithm provably finds the clique in linear time with high probability, provided $|\sC_N|\ge 1.261\sqrt{N}$ \cite{dekel2011finding}. Spectral methods can be shown to fail on cliques smaller than $\sqrt{N}$. In this paper we describe a nearly linear time algorithm that succeeds with high probability for $|\sC_N|\ge (1+\eps)\sqrt{N/e}$ for any $\eps>0$. This is the first algorithm that provably improves over spectral methods. We further generalize the hidden clique problem to other background graphs (the standard case corresponding to the complete graph on $N$ vertices). For large girth regular graphs of degree $(Δ+1)$ we prove that `local' algorithms succeed if $|\sC_N|\ge (1+\eps)N/\sqrt{eΔ}$ and fail if $|\sC_N|\le(1-\eps)N/\sqrt{eΔ}$.

math.PR↗

arXiv2013

Linear Bandits in High Dimension and Recommendation Systems

A large number of online services provide automated recommendations to help users to navigate through a large collection of items. New items (products, videos, songs, advertisements) are suggested on the basis of the user's past history and --when available-- her demographic profile. Recommendations have to satisfy the dual goal of helping the user to explore the space of available items, while allowing the system to probe the user's preferences. We model this trade-off using linearly parametrized multi-armed bandits, propose a policy and prove upper and lower bounds on the cumulative "reward" that coincide up to constants in the data poor (high-dimensional) regime. Prior work on linear bandits has focused on the data rich (low-dimensional) regime and used cumulative "risk" as the figure of merit. For this data rich regime, we provide a simple modification for our policy that achieves near-optimal risk performance under more restrictive assumptions on the geometry of the problem. We test (a variation of) the scheme used for establishing achievability on the Netflix and MovieLens datasets and obtain good agreement with the qualitative predictions of the theory we develop.

cs.LG↗

arXiv2012

Power Controlled Adaptive Sum-Capacity of Fading MACs with Distributed CSI

We consider the problem of finding optimal, fair and distributed power-rate strategies to achieve the sum capacity of the Gaussian multiple-access block-fading channel. In here, the transmitters have access to only their own fading coefficients, while the receiver has global access to all the fading coefficients. Outage is not permitted in any communication block. The resulting average sum-throughput is also known as `power-controlled adaptive sum-capacity', which appears as an open problem in literature. This paper presents the power-controlled adaptive sum-capacity of a wide-class of popular MAC models. In particular, we propose a power-rate strategy in the presence of distributed channel state information (CSI), which is throughput optimal when all the users have identical channel statistics. The proposed scheme also has an efficient implementation using successive cancellation and rate-splitting. We propose an upperbound when the channel laws are not identical. Furthermore, the optimal schemes are extended to situations in which each transmitter has additional finite-rate partial CSI on the link quality of others.

cs.IT↗