no code implementations • 19 Jul 2023 • Cian Eastwood, Shashank Singh, Andrei Liviu Nicolicioiu, Marin Vlastelica, Julius von Kügelgen, Bernhard Schölkopf
To avoid failures on out-of-distribution data, recent works have sought to extract features that have an invariant or stable relationship with the label across domains, discarding "spurious" or unstable features whose relationship with the label changes across domains.
1 code implementation • 20 Nov 2022 • Karan Uppal, Jaeah Kim, Shashank Singh
Eye-tracking has potential to provide rich behavioral data about human cognition in ecologically valid environments.
2 code implementations • 20 Jul 2022 • Cian Eastwood, Alexander Robey, Shashank Singh, Julius von Kügelgen, Hamed Hassani, George J. Pappas, Bernhard Schölkopf
By minimizing the $\alpha$-quantile of predictor's risk distribution over domains, QRM seeks predictors that perform well with probability $\alpha$.
no code implementations • 3 Jun 2022 • Shashank Singh
Traditional models of active learning assume a learner can directly manipulate or query a covariate $X$ in order to study its relationship with a response $Y$.
1 code implementation • 5 Jul 2021 • Shashank Singh, Justin Khim
The vast majority of statistical theory on binary classification characterizes performance in terms of accuracy.
no code implementations • 15 Oct 2020 • Shashank Singh
In both noiseless and noisy conditions, we derive minimax rates under simple and cumulative regrets.
no code implementations • NeurIPS 2020 • Sercan O. Arik, Chun-Liang Li, Jinsung Yoon, Rajarishi Sinha, Arkady Epshteyn, Long T. Le, Vikas Menon, Shashank Singh, Leyou Zhang, Nate Yoder, Martin Nikoltchev, Yash Sonthalia, Hootan Nakhost, Elli Kanal, Tomas Pfister
We propose a novel approach that integrates machine learning into compartmental disease modeling to predict the progression of COVID-19.
no code implementations • NeurIPS 2020 • Ananya Uppal, Shashank Singh, Barnabas Poczos
We study minimax convergence rates of nonparametric density estimation in the Huber contamination model, in which a proportion of the data comes from an unknown outlier distribution.
1 code implementation • 9 Apr 2020 • Justin Khim, Ziyu Xu, Shashank Singh
We study statistical properties of the k-nearest neighbors algorithm for multiclass classification, with a focus on settings where the number of classes may be large and/or classes may be highly imbalanced.
no code implementations • ICLR 2020 • Shashank Singh, Ashish Khetan, Zohar Karnin
In many learning situations, resources at inference time are significantly more constrained than resources at training time.
no code implementations • 20 May 2019 • Shashank Singh, Ashish Khetan, Zohar Karnin
In many learning situations, resources at inference time are significantly more constrained than resources at training time.
no code implementations • NeurIPS 2019 • Ananya Uppal, Shashank Singh, Barnabás Póczos
Thus, we show how our results imply bounds on the statistical error of a GAN, showing, for example, that GANs can strictly outperform the best linear estimator.
no code implementations • NeurIPS 2018 • Shashank Singh, Ananya Uppal, Boyue Li, Chun-Liang Li, Manzil Zaheer, Barnabás Póczos
We study minimax convergence rates of nonparametric density estimation under a large class of loss functions called "adversarial losses", which, besides classical $\mathcal{L}^p$ losses, includes maximum mean discrepancy (MMD), Wasserstein distance, and total variation distance.
no code implementations • 30 Mar 2018 • Shashank Singh, Bharath K. Sriperumbudur, Barnabás Póczos
We study estimation of (semi-)inner products between two nonparametric probability distributions, given IID samples from each distribution.
no code implementations • 24 Feb 2018 • Shashank Singh, Barnabás Póczos
The Wasserstein metric is an important measure of distance between probability distributions, with applications in machine learning, statistics, probability theory, and data analysis.
1 code implementation • 29 Aug 2017 • Shashank Singh, Barnabás Póczos, Jian Ma
Sparse dictionary learning (SDL) has become a popular method for adaptively identifying parsimonious representations of a dataset, a fundamental problem in machine learning and signal processing.
no code implementations • ICML 2017 • Shashank Singh, Barnabás Pøczos
To address this, we propose estimators for mutual information when $p$ is assumed to be a nonparanormal (a. k. a., Gaussian copula) model, a semiparametric compromise between Gaussian and nonparametric extremes.
no code implementations • NeurIPS 2016 • Shashank Singh, Barnabás Póczos
We provide finite-sample analysis of a general framework for using k-nearest neighbor statistics to estimate functionals of a nonparametric continuous probability density, including entropies and divergences.
1 code implementation • NeurIPS 2016 • Shashank Singh, Simon S. Du, Barnabás Póczos
Sobolev quantities (norms, inner products, and distances) of probability density functions are important in the theory of nonparametric statistics, but have rarely been used in practice, partly due to a lack of practical estimators.
no code implementations • 11 Apr 2016 • Shashank Singh, Sabrina Rashid, Zhicheng Long, Saket Navlakha, Hanna Salman, Zoltan N. Oltvai, Ziv Bar-Joseph
Communication and coordination play a major role in the ability of bacterial cells to adapt to ever changing environments and conditions.
Quantitative Methods
no code implementations • NeurIPS 2014 • Shashank Singh, Barnabás P óczos
We analyze a plug-in estimator for a large class of integral functionals of one or more continuous probability densities.
no code implementations • 28 Mar 2016 • Shashank Singh, Barnabás Póczos
Estimating divergences in a consistent way is of great importance in many machine learning tasks.
no code implementations • 28 Mar 2016 • Shashank Singh, Barnabás Póczos
Estimating entropy and mutual information consistently is important for many machine learning applications.