Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 12 of 12 for “"Rademacher complexity"”.
-
Chain rules for Rademacher complexity
… can be considered as a control over empirical Rademacher complexity of a composite function class. Such an estimate can be applied to learning problems where the hypotheses have composite structure or where more than one function is needed to determine the empirical loss.
-
Improved Multi-Task Learning Based on Local Rademacher Analysis
… risk of the learning hypothesis along with a complexity measure of that hypothesis. Although different complexity measures can be used in deriving error bounds, Rademacher complexity has received considerable attention in recent years, due to its superiority to other complexity measures. In …
-
Risk bounds for improper prediction procedures
… excess risk bounds in terms of offset Rademacher complexity for which only in-expectation guarantees were previously obtained.</p> <p>Our second result shows that offset Rademacher complexity yields upper bounds on the excess risk of iterative regularization schemes characterized by …
-
Approximating Bayes: Inference and Modeling
… of this thesis are new tools for studying the complexity/hardness of achieving approximation guarantees for Markov chain Monte Carlo (MCMC) in high-dimensional settings. The third contribution of this thesis is a theoretical framework for Bayesian analysis in the face of model misspecification …
-
Out-of-distributional risk bounds for neural operators with applications to the Helmholtz equation
… neural operators we establish upper bounds on Rademacher complexity. These bounds are instrumental in deriving the corresponding generalization error bounds. Furthermore, we leverage Gaussian-Banach spaces to shed light on the out-of-risk bounds of traditional neural operators and sequential …
-
Online and active learning of big networks: theory and algorithms
… (LLGC). I show that the empirical transductive Rademacher complexity of the function class for LLGC provides a natural criterion for active learning. The resulting active learning approach is to select a subset of nodes on a graph such that the empirical transductive Rademacher complexity of …
-
Bridging the Gap Between Approximation and Learning via Optimal Approximation by ReLU MLPs of Maximal Regularity
… classes of universal ReLU MLPs, the empirical Rademacher complexity of our class remains bounded even when its depth and width become arbitrarily large. Further, our class of MLPs achieves a near−optimal sample complexity of 𝒪(łog(N)/√{N}) when given N i.i.d. normalized sub−Gaussian training …
-
Model-based and data-driven approaches meet redundancy in signal processing
… chaining techniques, in order to upper bound the Rademacher complexity of each network's hypothesis class. Then, we leverage this estimate so as to deliver the desired generalization error bounds. Finally, we conduct several experiments -- on synthetic and real-world datasets -- validating our …
-
Semantic Models for Machine Learning
… analysis of the method's stability using Rademacher complexity, hence deriving the error bound for new data. We conclude the thesis by applying the described approaches to problems in the various fields of image, text, music application and medical analysis, describing several novel …
-
Practical learning in a private and noisy world
… with respect to this distance and show that the Rademacher complexity captures the sample complexity of this problem (up to a quadratic gap). As a consequence, we obtain new computationally efficient algorithms for testable proper learning of halfspaces and decision trees, sample-efficient …
-
Near-optimal sample complexity for noisy or 1-bit tensor completion
… tensor in ℝ^{NxNx...N}, the best sampling complexity achieved is O(rN^{d/2}) which can be obtained by a tensor nuclear-norm minimization problem. This bound is significantly larger than O(rdN), the number of free variables in a rank-r tensor. In this thesis, we prove that when r=O(1), we …
-
Nonlinear and geometric control methods in deep learning theory
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2026-12-01