Arrow Research search

Author name cluster

Suresh Venkatasubramanian

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

19 papers
2 author rows

Possible papers

19

TMLR Journal 2025 Journal Article

Counting Hours, Counting Losses: The Toll of Unpredictable Work Schedules on Financial Security

  • Pegah Nokhiz
  • Aravinda Kanchana Ruwanpathirana
  • Aditya Bhaskara
  • Suresh Venkatasubramanian

Financial instability is a pressing concern in the United States, with drivers that include growing employment disparities and insufficient wages. While research typically focuses on financial aspects such as income inequality in precarious work environments, there is a tendency to overlook the time-related aspect of unstable work schedules. The inability to rely on a consistent work schedule not only leads to burnout and conflicts between work and family life but also results in financial shocks that directly impact workers' income and assets. Unforeseen fluctuations in earnings pose challenges in financial planning, affecting decisions regarding savings and spending, and ultimately undermining individuals' long-term financial stability and well-being. Our objective in this study is to understand how unforeseen fluctuations in earnings exacerbate financial fragility by investigating the extent to which individuals' financial management depends on their ability to anticipate and plan for future events. To answer this question, we present a computational framework to model real-time consumption decisions under income uncertainty, drawing on advances in online planning and reinforcement learning (RL) with lookahead. We introduce a novel online algorithm that enables utility-maximizing agents to dynamically adapt consumption choices in response to financial shocks, leveraging partial deterministic information about future income. This approach forms the basis of our simulation framework, which models how workers manage consumption in the face of variable work schedules and the imperative to avoid financial ruin. Through theoretical analysis, we quantify the utility advantage conferred by varying levels of lookahead. Empirical simulations demonstrate how increased lookahead improves financial utility. That is, with this framework, we demonstrate both theoretically and empirically how a worker's capacity to anticipate schedule changes enhances their long-term utility. Conversely, the inability to predict future events can worsen workers' financial instability. Moreover, our framework enables us to explore policy interventions aimed at mitigating the problem of schedule uncertainty. By modeling both individual behavior and potential policy interventions (e.g., advance scheduling regulations), our framework draws on ideas from machine learning and reinforcement learning to inform economic questions surrounding information access in financial planning.

PDF Details

NeurIPS Conference 2021 Conference Paper

It's COMPASlicated: The Messy Relationship between RAI Datasets and Algorithmic Fairness Benchmarks

  • Michelle Bao
  • Angela Zhou
  • Samantha Zottola
  • Brian Brubach
  • Sarah Desmarais
  • Aaron Horowitz
  • Kristian Lum
  • Suresh Venkatasubramanian

Risk assessment instrument (RAI) datasets, particularly ProPublica’s COMPAS dataset, are commonly used in algorithmic fairness papers due to benchmarking practices of comparing algorithms on datasets used in prior work. In many cases, this data is used as a benchmark to demonstrate good performance without ac-counting for the complexities of criminal justice (CJ) processes. However, we show that pretrial RAI datasets can contain numerous measurement biases and errors, and due to disparities in discretion and deployment, algorithmic fairness applied to RAI datasets is limited in making claims about real-world outcomes. These reasons make the datasets a poor fit for benchmarking under assumptions of ground truth and real-world impact. Furthermore, conventional practices of simply replicating previous data experiments may implicitly inherit or edify normative positions without explicitly interrogating value-laden assumptions. Without con-text of how interdisciplinary fields have engaged in CJ research and context of how RAIs operate upstream and downstream, algorithmic fairness practices are misaligned for meaningful contribution in the context of CJ, and would benefit from transparent engagement with normative considerations and values related to fairness, justice, and equality. These factors prompt questions about whether benchmarks for intrinsically socio-technical systems like the CJ system can exist in a beneficial and ethical way.

PDF Details

NeurIPS Conference 2021 Conference Paper

Shapley Residuals: Quantifying the limits of the Shapley value for explanations

  • Indra Kumar
  • Carlos Scheidegger
  • Suresh Venkatasubramanian
  • Sorelle Friedler

Popular feature importance techniques compute additive approximations to nonlinear models by first defining a cooperative game describing the value of different subsets of the model's features, then calculating the resulting game's Shapley values to attribute credit additively between the features. However, the specific modeling settings in which the Shapley values are a poor approximation for the true game have not been well-described. In this paper we utilize an interpretation of Shapley values as the result of an orthogonal projection between vector spaces to calculate a residual representing the kernel component of that projection. We provide an algorithm for computing these residuals, characterize different modeling settings based on the value of the residuals, and demonstrate that they capture information about model predictions that Shapley values cannot. Shapley residuals can thus act as a warning to practitioners against overestimating the degree to which Shapley-value-based explanations give them insight into a model.

PDF Details

ICML Conference 2020 Conference Paper

Problems with Shapley-value-based explanations as feature importance measures

  • I. Elizabeth Kumar
  • Suresh Venkatasubramanian
  • Carlos Scheidegger
  • Sorelle A. Friedler

Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models. These methods define a cooperative game between the features of a model and distribute influence among these input elements using some form of the game’s unique Shapley values. Justification for these methods rests on two pillars: their desirable mathematical properties, and their applicability to specific motivations for explanations. We show that mathematical problems arise when Shapley values are used for feature importance and that the solutions to mitigate these necessarily induce further complexity, such as the need for causal reasoning. We also draw on additional literature to argue that Shapley values do not provide explanations which suit human-centric goals of explainability.

Details

TCS Journal 2020 Journal Article

The complexity of explaining neural networks through (group) invariants

  • Danielle Ensign
  • Scott Neville
  • Arnab Paul
  • Suresh Venkatasubramanian

Ever since the work of Minsky and Papert, it has been thought that neural networks derive their effectiveness by finding representations of the data that are invariant with respect to the task. In other words, the representations eliminate components of the data that vary in a way that is irrelevant. These invariants are naturally expressed with respect to group operations, and thus an understanding of these groups is key to explaining the effectiveness of the neural network. Moreover, a line of work in deep learning has shown that explicit knowledge of group invariants can lead to more effective training results. In this paper, we investigate the difficulty of discovering anything about these implicit invariants. Unfortunately, our main results are negative: we show that a variety of questions around investigating invariant representations are NP-hard, even in approximate settings. Moreover, these results do not depend on the kind of architecture used: in fact, our results follow as soon as the network architecture is powerful enough to be universal. The key idea behind our results is that if we can find the symmetries of a problem then we can solve it.

Details DOI

NeurIPS Conference 2019 Conference Paper

Disentangling Influence: Using disentangled representations to audit model predictions

  • Charles Marx
  • Richard Phillips
  • Sorelle Friedler
  • Carlos Scheidegger
  • Suresh Venkatasubramanian

Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect (model outcomes are influenced via proxy features). Feature influence can also be expressed in aggregate over the training or test data or locally with respect to a single point. Current research has typically focused on one of each of these dimensions. In this paper, we develop disentangled influence audits, a procedure to audit the indirect influence of features. Specifically, we show that disentangled representations provide a mechanism to identify proxy features in the dataset, while allowing an explicit computation of feature influence on either individual outcomes or aggregate-level outcomes. We show through both theory and experiments that disentangled influence audits can both detect proxy features and show, for each individual or in aggregate, which of these proxy features affects the classifier being audited the most. In this respect, our method is more powerful than existing methods for ascertaining feature influence.

PDF Details

IJCAI Conference 2009 Conference Paper

  • Piyush Rai
  • Hal Daumé III
  • Suresh Venkatasubramanian

We present a streaming model for large-scale classification (in the context of 2-SVM) by leveraging connections between learning and computational geometry. The streaming model imposes the constraint that only a single pass over the data is allowed. The 2-SVM is known to have an equivalent formulation in terms of the minimum enclosing ball (MEB) problem, and an efficient algorithm based on the idea of core sets exists (CVM) [Tsang et al. , 2005]. CVM learns a (1+ε)-approximate MEB for a set of points and yields an approximate solution to corresponding SVM instance. However CVM works in batch mode requiring multiple passes over the data. This paper presents a single-pass SVM which is based on the minimum enclosing ball of streaming data. We show that the MEB updates for the streaming case can be easily adapted to learn the SVM weight vector in a way similar to using online stochastic gradient updates. Our algorithm performs polylogarithmic computation at each example, and requires very small and constant storage. Experimental results show that, even in such restrictive settings, we can learn efficiently in just one pass and get accuracies comparable to other stateof-the-art SVM solvers (batch and online). We also give an analysis of the algorithm, and discuss some open issues and possible extensions.

PDF Details

YNIMG Journal 2009 Journal Article

The geometric median on Riemannian manifolds with application to robust atlas estimation

  • P. Thomas Fletcher
  • Suresh Venkatasubramanian
  • Sarang Joshi

One of the primary goals of computational anatomy is the statistical analysis of anatomical variability in large populations of images. The study of anatomical shape is inherently related to the construction of transformations of the underlying coordinate space, which map one anatomy to another. It is now well established that representing the geometry of shapes or images in Euclidian spaces undermines our ability to represent natural variability in populations. In our previous work we have extended classical statistical analysis techniques, such as averaging, principal components analysis, and regression, to Riemannian manifolds, which are more appropriate representations for describing anatomical variability. In this paper we extend the notion of robust estimation, a well established and powerful tool in traditional statistical analysis of Euclidian data, to manifold-valued representations of anatomical variability. In particular, we extend the geometric median, a classic robust estimator of centrality for data in Euclidean spaces. We formulate the geometric median of data on a Riemannian manifold as the minimizer of the sum of geodesic distances to the data points. We prove existence and uniqueness of the geometric median on manifolds with non-positive sectional curvature and give sufficient conditions for uniqueness on positively curved manifolds. Generalizing the Weiszfeld procedure for finding the geometric median of Euclidean data, we present an algorithm for computing the geometric median on an arbitrary manifold. We show that this algorithm converges to the unique solution when it exists. In this paper we exemplify the robustness of the estimation technique by applying the procedure to various manifolds commonly used in the analysis of medical images. Using this approach, we also present a robust brain atlas estimation technique based on the geometric median in the space of deformable images.

Details DOI

FOCS Conference 1997 Conference Paper

Storage Management for Evolving Databases

  • Jon M. Kleinberg
  • Rajeev Motwani 0001
  • Prabhakar Raghavan
  • Suresh Venkatasubramanian

The problem of maintaining data that arrives continuously over time is increasingly prevalent in databases and digital libraries. Building on a model for sliding window indices developed by N. Shivakumar and H. Garcia-Molina (1997), we devise efficient algorithms for some of the central problems that arise. We also show connections between the problems in this model and some fundamental problems in optimization and graph theory.

Details
v2026.09.13