English
Related papers

Related papers: Optimal Reconstruction from Linear Queries

200 papers

This paper provides new error bounds on "consistent" reconstruction methods for signals observed from quantized random projections. Those signal estimation techniques guarantee a perfect matching between the available quantized data and a…

Information Theory · Computer Science 2016-04-21 Laurent Jacques

We study algorithms for online linear optimization in Hilbert spaces, focusing on the case where the player is unconstrained. We develop a novel characterization of a large class of minimax algorithms, recovering, and even improving,…

Machine Learning · Computer Science 2014-05-22 H. Brendan McMahan , Francesco Orabona

We introduce and initiate the study of a new model of reductions called the random noise model. In this model, the truth table $T_f$ of the function $f$ is corrupted on a randomly chosen $\delta$-fraction of instances. A randomized…

Computational Complexity · Computer Science 2025-09-09 Tejas Nareddy , Abhishek Mishra

We study problem-dependent rates, i.e., generalization errors that scale near-optimally with the variance, the effective loss, or the gradient norms evaluated at the "best hypothesis." We introduce a principled framework dubbed "uniform…

Machine Learning · Statistics 2020-12-25 Yunbei Xu , Assaf Zeevi

We study the problem of identifying the parameters of a linear system from its response to multiple unknown waveforms. We assume that the system response is a scaled superposition of time-delayed and frequency-shifted versions of the…

Information Theory · Computer Science 2022-05-25 Mohamed A. Suliman , Wei Dai

This work studies approximation based on single-hidden-layer feedforward and recurrent neural networks with randomly generated internal weights. These methods, in which only the last layer of weights and a few hyperparameters are optimized,…

Probability · Mathematics 2021-02-17 Lukas Gonon , Lyudmila Grigoryeva , Juan-Pablo Ortega

Network reconstruction consists in retrieving the hidden interaction structure of a system from observations. Many reconstruction algorithms have been proposed, although less research has been devoted to describe their theoretical…

We consider signal reconstruction from the norms of subspace components generalizing standard phase retrieval problems. In the deterministic setting, a closed reconstruction formula is derived when the subspaces satisfy certain cubature…

Probability · Mathematics 2017-09-04 Christine Bachoc , Martin Ehler

We study the problem of reconstructing a signal from its projection on a subspace. The proposed signal reconstruction algorithms utilize a guiding subspace that represents desired properties of reconstructed signals. We show that optimal…

Information Theory · Computer Science 2016-06-13 Akshay Gadde , Andrew Knyazev , Dong Tian , Hassan Mansour

This paper considers the approximate reconstruction of points, x \in R^D, which are close to a given compact d-dimensional submanifold, M, of R^D using a small number of linear measurements of x. In particular, it is shown that a number of…

Information Theory · Computer Science 2012-04-17 Mark A. Iwen , Mauro Maggioni

The current paper studies the problem of agnostic $Q$-learning with function approximation in deterministic systems where the optimal $Q$-function is approximable by a function in the class $\mathcal{F}$ with approximation error $\delta \ge…

Machine Learning · Computer Science 2020-02-18 Simon S. Du , Jason D. Lee , Gaurav Mahajan , Ruosong Wang

We construct an adaptive asymptotically optimal in the classical norm of the space L(2) of square integrable functions non - parametrical multidimensional time defined signal regaining (adaptive filtration, noise canceller) on the…

Data Analysis, Statistics and Probability · Physics 2008-09-19 Eugene Ostrovsky , Leonid Sirota

The Levenshtein sequence reconstruction problem studies the reconstruction of a transmitted sequence from multiple erroneous copies of it. A fundamental question in this field is to determine the minimum number of erroneous copies required…

Information Theory · Computer Science 2026-01-21 Wentu Song , Kui Cai , Tony Q. S. Quek

The well-known trace reconstruction problem is the problem of inferring an unknown source string $x \in \{0,1\}^n$ from independent "traces", i.e. copies of $x$ that have been corrupted by a $\delta$-deletion channel which independently…

Data Structures and Algorithms · Computer Science 2022-11-08 Xi Chen , Anindya De , Chin Ho Lee , Rocco A. Servedio , Sandip Sinha

We consider the problem of learning to optimize an unknown Markov decision process (MDP). We show that, if the MDP can be parameterized within some known function class, we can obtain regret bounds that scale with the dimensionality, rather…

Machine Learning · Statistics 2014-11-04 Ian Osband , Benjamin Van Roy

We study model selection in linear bandits, where the learner must adapt to the dimension (denoted by $d_\star$) of the smallest hypothesis class containing the true linear model while balancing exploration and exploitation. Previous papers…

Machine Learning · Statistics 2022-03-17 Yinglun Zhu , Robert Nowak

Trace reconstruction is the problem of learning an unknown string $x$ from independent traces of $x$, where traces are generated by independently deleting each bit of $x$ with some deletion probability $q$. In this paper, we initiate the…

Data Structures and Algorithms · Computer Science 2020-12-15 Shyam Narayanan , Michael Ren

We show that reconstructing a curve in $\mathbb{R}^d$ for $d\geq 2$ from a $0.66$-sample is always possible using an algorithm similar to the classical NN-Crust algorithm. Previously, this was only known to be possible for $0.47$-samples in…

Computational Geometry · Computer Science 2022-03-11 Håvard Bakke Bjerkevik

We consider the problem of online adaptive control of the linear quadratic regulator, where the true system parameters are unknown. We prove new upper and lower bounds demonstrating that the optimal regret scales as…

Machine Learning · Computer Science 2023-10-05 Max Simchowitz , Dylan J. Foster

A critical vulnerability of supervised deep learning in high-dimensional tabular domains is "generalization collapse": models form precise decision boundaries around known training distributions but fail catastrophically when encountering…

Machine Learning · Computer Science 2026-03-10 Rajeeb Thapa Chhetri , Saurab Thapa , Avinash Kumar , Zhixiong Chen