English
Related papers

Related papers: Rigorous estimates for the relegation algorithm

200 papers

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by…

Machine Learning · Statistics 2020-08-28 Tomas Vaškevičius , Varun Kanade , Patrick Rebeschini

We use the uniform semiclassical approximation in order to derive the fidelity decay in the regime of large perturbations. Numerical computations are presented which agree with our theoretical predictions. Moreover, our theory allows to…

Quantum Physics · Physics 2016-09-08 Wen-ge Wang , G. Casati , Baowen Li , T. Prosen

We consider the setting of online logistic regression and consider the regret with respect to the 2-ball of radius B. It is known (see [Hazan et al., 2014]) that any proper algorithm which has logarithmic regret in the number of samples…

Machine Learning · Computer Science 2020-11-04 Rémi Jézéquel , Pierre Gaillard , Alessandro Rudi

This paper provides error analyses of the algorithms most commonly used for the evaluation of the Chebyshev polynomial of the first kind $T_N(x)$. Some of these algorithms are shown to be backward stable. This means that the computed value…

Numerical Analysis · Mathematics 2013-12-23 Alicja Smoktunowicz , Agata Smoktunowicz , Ewa Pawelec

Low-rank regularization (LRR) has been widely applied in various machine learning tasks, but the associated optimization is challenging. Directly optimizing the rank function under constraints is NP-hard in general. To overcome this…

Machine Learning · Computer Science 2025-05-22 Naiqi Li , Yuqiu Xie , Peiyuan Liu , Tao Dai , Yong Jiang , Shu-Tao Xia

This paper presents a detailed theoretical analysis of the three stochastic approximation proximal gradient algorithms proposed in our companion paper [49] to set regularization parameters by marginal maximum likelihood estimation. We prove…

Statistics Theory · Mathematics 2020-08-14 Valentin De Bortoli , Alain Durmus , Ana F. Vidal , Marcelo Pereyra

We present a subgradient method for minimizing non-smooth, non-Lipschitz convex optimization problems. The only structure assumed is that a strictly feasible point is known. We extend the work of Renegar [5] by taking a different…

Optimization and Control · Mathematics 2018-02-28 Benjamin Grimmer

Steepness is a geometric property which, together with complex-analyticity, is needed in order to insure stability of a near-integrable hamiltonian system over exponentially long times. Following a strategy developed by Nekhoro-shev, we…

Dynamical Systems · Mathematics 2020-11-20 Santiago Barbieri

We prove a $C^\infty$ version of the Nekhoroshev's estimate on the stability times of the actions in close to integrable Hamiltonian systems. The proof we give is a variant of the original Nekhoroshev's proof and it consists in first…

Dynamical Systems · Mathematics 2020-02-18 Dario Bambusi , Beatrice Langella

Conditional stability estimates require additional regularization for obtaining stable approximate solutions if the validity area of such estimates is not completely known. In this context, we consider ill-posed nonlinear inverse problems…

Numerical Analysis · Mathematics 2020-01-29 Frank Werner , Bernd Hofmann

The overall performance or expected excess risk of an iterative machine learning algorithm can be decomposed into training error and generalization error. While the former is controlled by its convergence analysis, the latter can be tightly…

Machine Learning · Statistics 2018-04-06 Yuansi Chen , Chi Jin , Bin Yu

We generalize the Safe Extremum Seeking algorithm to address the minimization of an unknown objective function subject to multiple unknown inequality and equality constraints, relying on recent results of gradient flow systems. These…

Optimization and Control · Mathematics 2025-10-09 Alan Williams , Jorge Cortés , Alexander Scheinker

The classical Eagleson's theorem states that if appropriately normalized Birkhoff sums generated by a measurable function and a probability preserving transformation converge in distribution, then they also converge in distribution with…

Dynamical Systems · Mathematics 2020-11-11 Yeor Hafouta

This paper aims at developing two versions of the generalized Newton method to compute not merely arbitrary local minimizers of nonsmooth optimization problems but just those, which possess an important stability property known as tilt…

Optimization and Control · Mathematics 2021-01-01 Boris Mordukhovich , Ebrahim Sarabi

Likelihood ratios are used for a variety of applications in particle physics data analysis, including parameter estimation, unfolding, and anomaly detection. When the data are high-dimensional, neural networks provide an effective tools for…

High Energy Physics - Phenomenology · Physics 2025-03-27 Fernando Torales Acosta , Tanvi Wamorkar , Vinicius Mikuni , Benjamin Nachman

In this paper, we address the efficient implementation of moving horizon state estimation of constrained discrete-time linear systems. We propose a novel iteration scheme which employs a proximity-based formulation of the underlying…

Optimization and Control · Mathematics 2021-11-09 Meriem Gharbi , Bahman Gharesifard , Christian Ebenbauer

We present a new perspective on the celebrated Sinkhorn algorithm by showing that is a special case of incremental/stochastic mirror descent. In order to see this, one should simply plug Kullback-Leibler divergence in both mirror map and…

Machine Learning · Computer Science 2019-09-17 Konstantin Mishchenko

In this paper, we study the online learning algorithm without explicit regularization terms. This algorithm is essentially a stochastic gradient descent scheme in a reproducing kernel Hilbert space (RKHS). The polynomially decaying step…

Machine Learning · Computer Science 2017-10-11 Zheng-Chu Guo , Lei Shi

This paper is about the surprising interaction of a foundational result from model theory, about stability of theories, with algorithmic stability in learning. First, in response to gaps in existing learning models, we introduce a new…

Logic · Mathematics 2025-07-04 Maryanthe Malliaris , Shay Moran

The inverse-free extreme learning machine (ELM) algorithm proposed in [4] was based on an inverse-free algorithm to compute the regularized pseudo-inverse, which was deduced from an inverse-free recursive algorithm to update the inverse of…

Machine Learning · Computer Science 2020-04-29 Hufei Zhu