More Like this

1. Sample Amplification: Increasing Dataset Size even when Learning is Impossible

   Axelrod, Brian; Garg, Shivam; Sharan, Vatsal; Valiant, Gregory (January 2020, International Conference on Machine Learning (ICML))

   Given data drawn from an unknown distribution, D, to what extent is it possible to ``amplify'' this dataset and faithfully output an even larger set of samples that appear to have been drawn from D? We formalize this question as follows: an (n,m) amplification procedure takes as input n independent draws from an unknown distribution D, and outputs a set of m > n ``samples'' which must be indistinguishable from m samples drawn iid from D. We consider this sample amplification problem in two fundamental settings: the case where D is an arbitrary discrete distribution supported on k elements, and the case where D is a d-dimensional Gaussian with unknown mean, and fixed covariance matrix. Perhaps surprisingly, we show a valid amplification procedure exists for both of these settings, even in the regime where the size of the input dataset, n, is significantly less than what would be necessary to learn distribution D to non-trivial accuracy. We also show that our procedures are optimal up to constant factors. Beyond these results, we describe potential applications of sample amplification, and formalize a number of curious directions for future research. 

   more » « less
2. Estimating Learnability in the Sublinear Data Regime

   Kong, Weihao; Valiant, Gregory (January 2018, Advances in neural information processing systems)

   We consider the problem of estimating how well a model class is capable of fitting a distribution of labeled data. We show that it is possible to accurately estimate this “learnability” even when given an amount of data that is too small to reliably learn any accurate model. Our first result applies to the setting where the data is drawn from a d-dimensional distribution with isotropic covariance, and the label of each datapoint is an arbitrary noisy function of the datapoint. In this setting, we show that with O(sqrt(d)) samples, one can accurately estimate the fraction of the variance of the label that can be explained via the best linear function of the data. For comparison, even if the labels are noiseless linear functions of the data, a sample size linear in the dimension, d, is required to learn any function correlated with the underlying model. Our estimation approach also applies to the setting where the data distribution has an (unknown) arbitrary covariance matrix, allowing these techniques to be applied to settings where the model class consists of a linear function applied to a nonlinear embedding of the data. In this setting we give a consistent estimator of the fraction of explainable variance that uses o(d) samples. Finally, our techniques also extend to the setting of binary classification, where we obtain analogous results under the logistic model, for estimating the classification accuracy of the best linear classifier. We demonstrate the practical viability of our approaches on synthetic and real data. This ability to estimate the explanatory value of a set of features (or dataset), even in the regime in which there is too little data to realize that explanatory value, may be relevant to the scientific and industrial settings for which data collection is expensive and there are many potentially relevant feature sets that could be collected. 

   more » « less
3. Outlier robust multivariate polynomial regression

   Arora, Vipul; Bhattacharyya, Arnab; Boban, Mathews; Guruswami, Venkatesan; Kelman, Esty (September 0024, Proceedings of the European Symposium on Algorithms (ESA),)

   We study the problem of robust multivariate polynomial regression: let p\colon\mathbb{R}^n\to\mathbb{R} be an unknown n-variate polynomial of degree at most d in each variable. We are given as input a set of random samples (\mathbf{x}_i,y_i) \in [-1,1]^n \times \mathbb{R} that are noisy versions of (\mathbf{x}_i,p(\mathbf{x}_i)). More precisely, each \mathbf{x}_i is sampled independently from some distribution \chi on [-1,1]^n, and for each i independently, y_i is arbitrary (i.e., an outlier) with probability at most \rho < 1/2, and otherwise satisfies |y_i-p(\mathbf{x}_i)|\leq\sigma. The goal is to output a polynomial \hat{p}, of degree at most d in each variable, within an \ell_\infty-distance of at most O(\sigma) from p. Kane, Karmalkar, and Price [FOCS'17] solved this problem for n=1. We generalize their results to the n-variate setting, showing an algorithm that achieves a sample complexity of O_n(d^n\log d), where the hidden constant depends on n, if \chi is the n-dimensional Chebyshev distribution. The sample complexity is O_n(d^{2n}\log d), if the samples are drawn from the uniform distribution instead. The approximation error is guaranteed to be at most O(\sigma), and the run-time depends on \log(1/\sigma). In the setting where each \mathbf{x}_i and y_i are known up to N bits of precision, the run-time's dependence on N is linear. We also show that our sample complexities are optimal in terms of d^n. Furthermore, we show that it is possible to have the run-time be independent of 1/\sigma, at the cost of a higher sample complexity. 

   more » « less
4. Outlier Robust Multivariate Polynomial Regression

   https://doi.org/10.4230/LIPIcs.ESA.2024.12  

   Arora, Vipul; Bhattacharyya, Arnab; Boban, Mathews; Guruswami, Venkatesan; Kelman, Esty (January 2024, Schloss Dagstuhl – Leibniz-Zentrum für Informatik)

   Chan, Timothy; Fischer, Johannes; Iacono, John; Herman, Grzegorz (Ed.)

   We study the problem of robust multivariate polynomial regression: let p: ℝⁿ → ℝ be an unknown n-variate polynomial of degree at most d in each variable. We are given as input a set of random samples (𝐱_i,y_i) ∈ [-1,1]ⁿ × ℝ that are noisy versions of (𝐱_i,p(𝐱_i)). More precisely, each 𝐱_i is sampled independently from some distribution χ on [-1,1]ⁿ, and for each i independently, y_i is arbitrary (i.e., an outlier) with probability at most ρ < 1/2, and otherwise satisfies |y_i-p(𝐱_i)| ≤ σ. The goal is to output a polynomial p̂, of degree at most d in each variable, within an 𝓁_∞-distance of at most O(σ) from p. Kane, Karmalkar, and Price [FOCS'17] solved this problem for n = 1. We generalize their results to the n-variate setting, showing an algorithm that achieves a sample complexity of O_n(dⁿlog d), where the hidden constant depends on n, if χ is the n-dimensional Chebyshev distribution. The sample complexity is O_n(d^{2n}log d), if the samples are drawn from the uniform distribution instead. The approximation error is guaranteed to be at most O(σ), and the run-time depends on log(1/σ). In the setting where each 𝐱_i and y_i are known up to N bits of precision, the run-time’s dependence on N is linear. We also show that our sample complexities are optimal in terms of dⁿ. Furthermore, we show that it is possible to have the run-time be independent of 1/σ, at the cost of a higher sample complexity. 

   more » « less
5. Sample-Optimal Identity Testing with High Probability

   Diakonikolas, Ilias; Gouleakis, Themis; Peebles, John; Price, Eric (July 2018, 45th International Colloquium on Automata, Languages, and Automata)

   We study the problem of testing identity against a given distribution with a focus on the high confidence regime. More precisely, given samples from an unknown distribution p over n elements, an explicitly given distribution q, and parameters 0< epsilon, delta < 1, we wish to distinguish, with probability at least 1-delta, whether the distributions are identical versus epsilon-far in total variation distance. Most prior work focused on the case that delta = Omega(1), for which the sample complexity of identity testing is known to be Theta(sqrt{n}/epsilon^2). Given such an algorithm, one can achieve arbitrarily small values of delta via black-box amplification, which multiplies the required number of samples by Theta(log(1/delta)). We show that black-box amplification is suboptimal for any delta = o(1), and give a new identity tester that achieves the optimal sample complexity. Our new upper and lower bounds show that the optimal sample complexity of identity testing is Theta((1/epsilon^2) (sqrt{n log(1/delta)} + log(1/delta))) for any n, epsilon, and delta. For the special case of uniformity testing, where the given distribution is the uniform distribution U_n over the domain, our new tester is surprisingly simple: to test whether p = U_n versus d_{TV} (p, U_n) >= epsilon, we simply threshold d_{TV}({p^}, U_n), where {p^} is the empirical probability distribution. The fact that this simple "plug-in" estimator is sample-optimal is surprising, even in the constant delta case. Indeed, it was believed that such a tester would not attain sublinear sample complexity even for constant values of epsilon and delta. An important contribution of this work lies in the analysis techniques that we introduce in this context. First, we exploit an underlying strong convexity property to bound from below the expectation gap in the completeness and soundness cases. Second, we give a new, fast method for obtaining provably correct empirical estimates of the true worst-case failure probability for a broad class of uniformity testing statistics over all possible input distributions - including all previously studied statistics for this problem. We believe that our novel analysis techniques will be useful for other distribution testing problems as well. 

   more » « less