Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Sahil Garg, Anderson Schneider, Anant Raj, Kashif Rasul, Yuriy Nevmyvaka, Sneihil Gopal, Amit Dhurandhar, Guillermo Cecchi, Irina Rish

Building on the remarkable achievements in generative sampling of natural images, we propose an innovative challenge, potentially overly ambitious, which involves generating samples of entire multivariate time series that resemble images. However, the statistical challenge lies in the small sample size, sometimes consisting of a few hundred subjects. This issue is especially problematic for deep generative models that follow the conventional approach of generating samples from a canonical distribution and then decoding or denoising them to match the true data distribution. In contrast, our method is grounded in information theory and aims to implicitly characterize the distribution of images, particularly the (global and local) dependency structure between pixels. We achieve this by empirically estimating its KL-divergence in the dual form with respect to the respective marginal distribution. This enables us to perform generative sampling directly in the optimized 1-D dual divergence space. Specifically, in the dual space, training samples representing the data distribution are embedded in the form of various clusters between two end points. In theory, any sample embedded between those two end points is in-distribution w.r.t. the data distribution. Our key idea for generating novel samples of images is to interpolate between the clusters via a walk as per gradients of the dual function w.r.t. the data dimensions. In addition to the data efficiency gained from direct sampling, we propose an algorithm that offers a significant reduction in sample complexity for estimating the divergence of the data distribution with respect to the marginal distribution. We provide strong theoretical guarantees along with an extensive empirical evaluation using many real-world datasets from diverse domains, establishing the superiority of our approach w.r.t. state-of-the-art deep learning methods.

Via

Saurabh Mishra, Anant Raj, Sharan Vaswani

Inverse optimization involves inferring unknown parameters of an optimization problem from known solutions, and is widely used in fields such as transportation, power systems and healthcare. We study the contextual inverse optimization setting that utilizes additional contextual information to better predict the unknown problem parameters. We focus on contextual inverse linear programming (CILP), addressing the challenges posed by the non-differentiable nature of LPs. For a linear prediction model, we reduce CILP to a convex feasibility problem allowing the use of standard algorithms such as alternating projections. The resulting algorithm for CILP is equipped with a linear convergence guarantee without additional assumptions such as degeneracy or interpolation. Next, we reduce CILP to empirical risk minimization (ERM) on a smooth, convex loss that satisfies the Polyak-Lojasiewicz condition. This reduction enables the use of scalable first-order optimization methods to solve large non-convex problems, while maintaining theoretical guarantees in the convex setting. Finally, we experimentally validate our approach on both synthetic and real-world problems, and demonstrate improved performance compared to existing methods.

Via

Yikai Zhang, Songzhu Zheng, Mina Dalirrooyfard, Pengxiang Wu, Anderson Schneider, Anant Raj, Yuriy Nevmyvaka, Chao Chen

Learning and decision-making in domains with naturally high noise-to-signal ratio, such as Finance or Healthcare, is often challenging, while the stakes are very high. In this paper, we study the problem of learning and acting under a general noisy generative process. In this problem, the data distribution has a significant proportion of uninformative samples with high noise in the label, while part of the data contains useful information represented by low label noise. This dichotomy is present during both training and inference, which requires the proper handling of uninformative data during both training and testing. We propose a novel approach to learning under these conditions via a loss inspired by the selective learning theory. By minimizing this loss, the model is guaranteed to make a near-optimal decision by distinguishing informative data from uninformative data and making predictions. We build upon the strength of our theoretical guarantees by describing an iterative algorithm, which jointly optimizes both a predictor and a selector, and evaluates its empirical performance in a variety of settings.

Via

Lingjiong Zhu, Mert Gurbuzbalaban, Anant Raj, Umut Simsekli

Algorithmic stability is an important notion that has proven powerful for deriving generalization bounds for practical algorithms. The last decade has witnessed an increasing number of stability bounds for different algorithms applied on different classes of loss functions. While these bounds have illuminated various properties of optimization algorithms, the analysis of each case typically required a different proof technique with significantly different mathematical tools. In this study, we make a novel connection between learning theory and applied probability and introduce a unified guideline for proving Wasserstein stability bounds for stochastic optimization algorithms. We illustrate our approach on stochastic gradient descent (SGD) and we obtain time-uniform stability bounds (i.e., the bound does not increase with the number of iterations) for strongly convex losses and non-convex losses with additive noise, where we recover similar results to the prior art or extend them to more general cases by using a single proof technique. Our approach is flexible and can be generalizable to other popular optimizers, as it mainly requires developing Lyapunov functions, which are often readily available in the literature. It also illustrates that ergodicity is an important component for obtaining time-uniform bounds -- which might not be achieved for convex or non-convex losses unless additional noise is injected to the iterates. Finally, we slightly stretch our analysis technique and prove time-uniform bounds for SGD under convex and non-convex losses (without additional additive noise), which, to our knowledge, is novel.

Via

Anant Raj, Umut Şimşekli, Alessandro Rudi

This paper deals with the problem of efficient sampling from a stochastic differential equation, given the drift function and the diffusion matrix. The proposed approach leverages a recent model for probabilities \citep{rudi2021psd} (the positive semi-definite -- PSD model) from which it is possible to obtain independent and identically distributed (i.i.d.) samples at precision $\varepsilon$ with a cost that is $m^2 d \log(1/\varepsilon)$ where $m$ is the dimension of the model, $d$ the dimension of the space. The proposed approach consists in: first, computing the PSD model that satisfies the Fokker-Planck equation (or its fractional variant) associated with the SDE, up to error $\varepsilon$, and then sampling from the resulting PSD model. Assuming some regularity of the Fokker-Planck solution (i.e. $\beta$-times differentiability plus some geometric condition on its zeros) We obtain an algorithm that: (a) in the preparatory phase obtains a PSD model with L2 distance $\varepsilon$ from the solution of the equation, with a model of dimension $m = \varepsilon^{-(d+1)/(\beta-2s)} (\log(1/\varepsilon))^{d+1}$ where $0<s\leq1$ is the fractional power to the Laplacian, and total computational complexity of $O(m^{3.5} \log(1/\varepsilon))$ and then (b) for Fokker-Planck equation, it is able to produce i.i.d.\ samples with error $\varepsilon$ in Wasserstein-1 distance, with a cost that is $O(d \varepsilon^{-2(d+1)/\beta-2} \log(1/\varepsilon)^{2d+3})$ per sample. This means that, if the probability associated with the SDE is somewhat regular, i.e. $\beta \geq 4d+2$, then the algorithm requires $O(\varepsilon^{-0.88} \log(1/\varepsilon)^{4.5d})$ in the preparatory phase, and $O(\varepsilon^{-1/2}\log(1/\varepsilon)^{2d+2})$ for each sample. Our results suggest that as the true solution gets smoother, we can circumvent the curse of dimensionality without requiring any sort of convexity.

Via

Belinda Tzen, Anant Raj, Maxim Raginsky, Francis Bach

Mirror descent, introduced by Nemirovski and Yudin in the 1970s, is a primal-dual convex optimization method that can be tailored to the geometry of the optimization problem at hand through the choice of a strongly convex potential function. It arises as a basic primitive in a variety of applications, including large-scale optimization, machine learning, and control. This paper proposes a variational formulation of mirror descent and of its stochastic variant, mirror Langevin dynamics. The main idea, inspired by the classic work of Brezis and Ekeland on variational principles for gradient flows, is to show that mirror descent emerges as a closed-loop solution for a certain optimal control problem, and the Bellman value function is given by the Bregman divergence between the initial condition and the global minimizer of the objective function.

Via

Anant Raj, Lingjiong Zhu, Mert Gürbüzbalaban, Umut Şimşekli

Heavy-tail phenomena in stochastic gradient descent (SGD) have been reported in several empirical studies. Experimental evidence in previous works suggests a strong interplay between the heaviness of the tails and generalization behavior of SGD. To address this empirical phenomena theoretically, several works have made strong topological and statistical assumptions to link the generalization error to heavy tails. Very recently, new generalization bounds have been proven, indicating a non-monotonic relationship between the generalization error and heavy tails, which is more pertinent to the reported empirical observations. While these bounds do not require additional topological assumptions given that SGD can be modeled using a heavy-tailed stochastic differential equation (SDE), they can only apply to simple quadratic problems. In this paper, we build on this line of research and develop generalization bounds for a more general class of objective functions, which includes non-convex functions as well. Our approach is based on developing Wasserstein stability bounds for heavy-tailed SDEs and their discretizations, which we then convert to generalization bounds. Our results do not require any nontrivial assumptions; yet, they shed more light to the empirical observations, thanks to the generality of the loss functions.

Via

Gyanendra Das, Xavier Thomas, Anant Raj, Vikram Gupta

A large number of annotated video-caption pairs are required for training video captioning models, resulting in high annotation costs. Active learning can be instrumental in reducing these annotation requirements. However, active learning for video captioning is challenging because multiple semantically similar captions are valid for a video, resulting in high entropy outputs even for less-informative samples. Moreover, video captioning algorithms are multimodal in nature with a visual encoder and language decoder. Further, the sequential and combinatorial nature of the output makes the problem even more challenging. In this paper, we introduce MAViC which leverages our proposed Multimodal Semantics Aware Sequential Entropy (M-SASE) based acquisition function to address the challenges of active learning approaches for video captioning. Our approach integrates semantic similarity and uncertainty of both visual and language dimensions in the acquisition function. Our detailed experiments empirically demonstrate the efficacy of M-SASE for active learning for video captioning and improve on the baselines by a large margin.

Via

Antonio Orvieto, Anant Raj, Hans Kersting, Francis Bach

Injecting noise within gradient descent has several desirable features. In this paper, we explore noise injection before computing a gradient step, which is known to have smoothing and regularizing properties. We show that small perturbations induce explicit regularization for simple finite-dimensional models based on the l1-norm, group l1-norms, or nuclear norms. When applied to overparametrized neural networks with large widths, we show that the same perturbations do not work due to variance explosion resulting from overparametrization. However, we also show that independent layer wise perturbations allow to avoid the exploding variance term, and explicit regularizers can then be obtained. We empirically show that the small perturbations lead to better generalization performance than vanilla (stochastic) gradient descent training, with minor adjustments to the training procedure.

Via