no code implementations • 10 Oct 2023 • Shyam Narayanan
First, we prove that for any $\alpha \le O(1)$, estimating the covariance of a Gaussian up to spectral error $\alpha$ requires $\tilde{\Omega}\left(\frac{d^{3/2}}{\alpha \varepsilon} + \frac{d}{\alpha^2}\right)$ samples, which is tight up to logarithmic factors.
no code implementations • 31 Aug 2023 • Shyam Narayanan, Matteo Cartiglia, Arianna Rubino, Charles Lego, Charlotte Frenkel, Giacomo Indiveri
Low-power event-based analog front-ends (AFE) are a crucial component required to build efficient end-to-end neuromorphic processing systems for edge computing.
no code implementations • 24 Jul 2023 • Sitan Chen, Shyam Narayanan
We revisit the well-studied problem of learning a linear combination of $k$ ReLU activations given labeled examples drawn from the standard $d$-dimensional Gaussian measure.
1 code implementation • 20 Jun 2023 • Anders Aamand, Alexandr Andoni, Justin Y. Chen, Piotr Indyk, Shyam Narayanan, Sandeep Silwal
We study statistical/computational tradeoffs for the following density estimation problem: given $k$ distributions $v_1, \ldots, v_k$ over a discrete domain of size $n$, and sampling access to a distribution $p$, identify $v_i$ that is "close" to $p$.
no code implementations • 15 Apr 2023 • Nicholas Schiefer, Justin Y. Chen, Piotr Indyk, Shyam Narayanan, Sandeep Silwal, Tal Wagner
An $\varepsilon$-approximate quantile sketch over a stream of $n$ inputs approximates the rank of any query point $q$ - that is, the number of input points less than $q$ - up to an additive error of $\varepsilon n$, generally with some probability of at least $1 - 1/\mathrm{poly}(n)$, while consuming $o(n)$ space.
no code implementations • 6 Apr 2023 • Ainesh Bakshi, Shyam Narayanan
In particular, for Spectral LRA, we show that any algorithm requires $\Omega\left(\log(n)/\varepsilon^{1/2}\right)$ matrix-vector products, exactly matching the upper bound obtained by Krylov methods [MM15, BCW22].
no code implementations • 5 Apr 2023 • Sinho Chewi, Jaume de Dios Pont, Jerry Li, Chen Lu, Shyam Narayanan
Log-concave sampling has witnessed remarkable algorithmic advances in recent years, but the corresponding problem of proving lower bounds for this task has remained elusive, with lower bounds previously known only in dimension one.
no code implementations • 9 Dec 2022 • Samuel B. Hopkins, Gautam Kamath, Mahbod Majid, Shyam Narayanan
We study the relationship between adversarial robustness and differential privacy in high-dimensional algorithmic statistics.
no code implementations • 6 Nov 2022 • Anders Aamand, Justin Y. Chen, Piotr Indyk, Shyam Narayanan, Ronitt Rubinfeld, Nicholas Schiefer, Sandeep Silwal, Tal Wagner
However, those simulations involve neural networks for the 'combine' function of size polynomial or even exponential in the number of graph nodes $n$, as well as feature vectors of length linear in $n$.
no code implementations • 11 Apr 2022 • Vincent Cohen-Addad, Hossein Esfandiari, Vahab Mirrokni, Shyam Narayanan
Motivated by data analysis and machine learning applications, we consider the popular high-dimensional Euclidean $k$-median and $k$-means problems.
no code implementations • ICLR 2022 • Justin Y. Chen, Talya Eden, Piotr Indyk, Honghao Lin, Shyam Narayanan, Ronitt Rubinfeld, Sandeep Silwal, Tal Wagner, David P. Woodruff, Michael Zhang
We propose data-driven one-pass streaming algorithms for estimating the number of triangles and four cycles, two fundamental problems in graph analytics that are widely studied in the graph data stream literature.
no code implementations • 3 Mar 2022 • Shyam Narayanan
Our results improve over the previous best work of Canonne et al.~\cite{CanonneKMUZ20} for both computationally efficient and inefficient algorithms, and even our computationally efficient algorithm matches the optimal \emph{non-private} sample complexity of $O\left(\frac{\sqrt{d}}{\alpha^2}\right)$ in many standard parameter settings.
no code implementations • 22 Oct 2021 • Hossein Esfandiari, Vahab Mirrokni, Shyam Narayanan
In particular, we provide a nearly optimal trade-off between the number of users and the number of samples per user required for private mean estimation, even when the number of users is as low as $O(\frac{1}{\varepsilon}\log\frac{1}{\delta})$.
no code implementations • 5 Jul 2021 • Shyam Narayanan, Sandeep Silwal, Piotr Indyk, Or Zamir
Random dimensionality reduction is a versatile tool for speeding up algorithms for high-dimensional problems.
no code implementations • 1 Jul 2021 • Hossein Esfandiari, Vahab Mirrokni, Shyam Narayanan
Next, we study the $k$-means problem in this context and provide an $O(k \log k)$-approximation algorithm for explainable $k$-means, improving over the $O(k^2)$ bound of Dasgupta et al. and the $O(d k \log k)$ bound of \cite{laber2021explainable}.
no code implementations • ICLR 2021 • Talya Eden, Piotr Indyk, Shyam Narayanan, Ronitt Rubinfeld, Sandeep Silwal, Tal Wagner
We consider the problem of estimating the number of distinct elements in a large data set (or, equivalently, the support size of the distribution induced by the data set) from a random sample of its elements.
no code implementations • 23 Nov 2020 • Josh Alman, Timothy Chu, Gary Miller, Shyam Narayanan, Mark Sellke, Zhao Song
This completes the theory of Manhattan to Manhattan metric transforms initiated by Assouad in 1980.
no code implementations • 22 Oct 2018 • Shyam Narayanan, Jelani Nelson
$$ We show that a strictly stronger version of this statement holds, answering one of the main open questions of [MMMR18]: "$\forall y\in X$" in the above statement may be replaced with "$\forall y\in\mathbb R^d$", so that $f$ not only preserves distances within $X$, but also distances to $X$ from the rest of space.