Zobrazeno 1 - 10
of 373
pro vyhledávání: '"Tiegel, A."'
We present a polynomial-time reduction from solving noisy linear equations over $\mathbb{Z}/q\mathbb{Z}$ in dimension $\Theta(k\log n/\mathsf{poly}(\log k,\log q,\log\log n))$ with a uniformly random coefficient matrix to noisy linear equations over
Externí odkaz:
http://arxiv.org/abs/2411.12512
We prove that there is a universal constant $C>0$ so that for every $d \in \mathbb N$, every centered subgaussian distribution $\mathcal D$ on $\mathbb R^d$, and every even $p \in \mathbb N$, the $d$-variate polynomial $(Cp)^{p/2} \cdot \|v\|_{2}^p -
Externí odkaz:
http://arxiv.org/abs/2410.21194
Autor:
Dmitriev, Daniil, Buhai, Rares-Darius, Tiegel, Stefan, Wolters, Alexander, Novikov, Gleb, Sanyal, Amartya, Steurer, David, Yang, Fanny
We study the problem of estimating the means of well-separated mixtures when an adversary may add arbitrary outliers. While strong guarantees are available when the outlier fraction is significantly smaller than the minimum mixing weight, much less i
Externí odkaz:
http://arxiv.org/abs/2407.15792
Rubinfeld & Vasilyan recently introduced the framework of testable learning as an extension of the classical agnostic model. It relaxes distributional assumptions which are difficult to verify by conditions that can be checked efficiently by a tester
Externí odkaz:
http://arxiv.org/abs/2406.06106
Autor:
Tiegel, Stefan
We show strong (and surprisingly simple) lower bounds for weakly learning intersections of halfspaces in the improper setting. Strikingly little is known about this problem. For instance, it is not even known if there is a polynomial-time algorithm f
Externí odkaz:
http://arxiv.org/abs/2402.15995
We study computational-statistical gaps for improper learning in sparse linear regression. More specifically, given $n$ samples from a $k$-sparse linear model in dimension $d$, we ask what is the minimum sample complexity to efficiently (in time poly
Externí odkaz:
http://arxiv.org/abs/2402.14103
We study the problem of robustly estimating the mean or location parameter without moment assumptions. We show that for a large class of symmetric distributions, the same error as in the Gaussian setting can be achieved efficiently. The distributions
Externí odkaz:
http://arxiv.org/abs/2302.10844
Autor:
Chen, Hongjie, Cohen-Addad, Vincent, d'Orsi, Tommaso, Epasto, Alessandro, Imola, Jacob, Steurer, David, Tiegel, Stefan
We introduce general tools for designing efficient private estimation algorithms, in the high-dimensional settings, whose statistical guarantees almost match those of the best known non-private algorithms. To illustrate our techniques, we consider tw
Externí odkaz:
http://arxiv.org/abs/2301.04822
Autor:
Tiegel, Stefan
We show hardness of improperly learning halfspaces in the agnostic model, both in the distribution-independent as well as the distribution-specific setting, based on the assumption that worst-case lattice problems, such as GapSVP or SIVP, are hard. I
Externí odkaz:
http://arxiv.org/abs/2207.14030
We develop the first fast spectral algorithm to decompose a random third-order tensor over $\mathbb{R}^d$ of rank up to $O(d^{3/2}/\text{polylog}(d))$. Our algorithm only involves simple linear algebra operations and can recover all components in tim
Externí odkaz:
http://arxiv.org/abs/2202.06442