English
Related papers

Related papers: AdaBoost Does Not Always Cycle: A Computer-Assiste…

200 papers

ADAGB2, a generalization of the Adagrad algorithm for stochastic optimization is introduced, which is also applicable to bound-constrained problems and capable of using second-order information when available. It is shown that, given…

Optimization and Control · Mathematics 2025-05-13 S. Bellavia , S. Gratton , B. Morini , Ph. L. Toint

Schapire's margin theory provides a theoretical explanation to the success of boosting-type methods and manifests that a good margin distribution (MD) of training samples is essential for generalization. However the statement that a MD is…

Machine Learning · Computer Science 2012-08-10 Guangxu Guo , Songcan Chen

In heap-based languages, knowing that a variable x points to an acyclic data structure is useful for analyzing termination: this information guarantees that the depth of the data structure to which x points is greater than the depth of the…

Programming Languages · Computer Science 2014-05-20 Damiano Zanardini , Samir Genaim

In classical machine learning, a set of weak classifiers can be adaptively combined to form a strong classifier for improving the overall performance, a technique called adaptive boosting (or AdaBoost). However, constructing the strong…

Quantum Physics · Physics 2019-02-05 Ximing Wang , Yuechi Ma , Min-Hsiu Hsieh , Manhong Yung

In this overview article we will consider the deliberate restarting of algorithms, a meta technique, in order to improve the algorithm's performance, e.g., convergence rates or approximation guarantees. One of the major advantages is that…

Optimization and Control · Mathematics 2020-06-29 Sebastian Pokutta

Periodic orbits are fundamental to understand the dynamics of nonlinear systems. In this work, we focus on two aspects of interest regarding periodic orbits, in the context of a dissipative mapping, derived from a prototype model of a…

Chaotic Dynamics · Physics 2020-12-22 Danilo Rodrigues de Lima , Iberê Luiz Caldas

We study the cost of parallelizing weak-to-strong boosting algorithms for learning, following the recent work of Karbasi and Larsen. Our main results are two-fold: - First, we prove a tight lower bound, showing that even "slight"…

Machine Learning · Computer Science 2024-02-26 Xin Lyu , Hongxun Wu , Junzhao Yang

Dynamic logic is a modal logic for reasoning about programs. A cyclic proof system is a proof system that allows proofs containing cycles and is an alternative to a proof system containing (co-)induction. This paper introduces a sequent…

Logic in Computer Science · Computer Science 2026-03-03 Yukihiro Oda

An analysis of stick-slip behavior and convergence of trajectories in the feedback-controlled motion systems with discontinuous Coulomb friction is provided. A closed-form parameter-dependent stiction region, around an invariant equilibrium…

Systems and Control · Electrical Eng. & Systems 2021-09-30 Michael Ruderman

Christoph, Dragani\'{c}, Gir\~{a}o, Hurley, Michel, and M\"{u}yesser conjectured that, when $d\mid n$, the expected number of cycles in a uniformly random cycle-factor of a directed $d$-regular graph on $n$ vertices is uniquely maximised by…

Combinatorics · Mathematics 2026-05-08 Rishikesh Gajjala

We compare the divergence of orbits and the reversibility error for discrete time dynamical systems. These two quantities are used to explore the behavior of the global error induced by round off in the computation of orbits. The similarity…

Dynamical Systems · Mathematics 2012-11-15 Davide Faranda , Martin Federico Mestre , Giorgio Turchetti

We give necessary and sufficient conditions for a sequence to be exactly realizable as the sequence of numbers of periodic points in a dynamical system. Using these conditions, we show that no non-constant polynomial is realizable, and give…

Dynamical Systems · Mathematics 2007-05-23 Yash Puri , Thomas Ward

It is shown that adiabatic cycles excite a quantum particle, which is confined in a one-dimensional region and is initially in an eigenstate. During the cycle, an infinitely sharp wall is applied and varied its strength and position. After…

Quantum Physics · Physics 2016-04-20 Sho Kasumie , Manabu Miyamoto , Atushi Tanaka

Boosting is a general method of generating many simple classification rules and combining them into a single, highly accurate rule. In this talk, I will review the AdaBoost boosting algorithm and some of its underlying theory, and then look…

Machine Learning · Computer Science 2013-01-07 Robert E. Schapire

We prove that the maximal number of limit cycles which bifurcate from an open period annulus under a given multi-parameter analytic deformation of a given analytic vector field is the same as in an appropriate one-parameter analytic…

Dynamical Systems · Mathematics 2010-05-04 Lubomir Gavrilov

We consider convex SGD updates with a block-cyclic structure, i.e. where each cycle consists of a small number of blocks, each with many samples from a possibly different, block-specific, distribution. This situation arises, e.g., in…

Machine Learning · Computer Science 2019-04-24 Hubert Eichner , Tomer Koren , H. Brendan McMahan , Nathan Srebro , Kunal Talwar

The paper addresses the problem of computing maximal expected time to termination of probabilistic timed automata (PTA) models, under the condition that the system will, eventually, terminate. This problem can exhibit high computational…

Formal Languages and Automata Theory · Computer Science 2018-03-23 Omar Al-Bataineh , Michael Fisher , David Rosenblum

In this paper, we will report our efforts in designing closed-loop feedback for the thruster-assisted walking of bipedal robots. We will assume for well-tuned supervisory controllers and will focus on fine-tuning the joints desired…

Robotics · Computer Science 2020-05-04 Pravin Dangol , Alireza Ramezani

A heterodimensional cycle is an invariant set of a dynamical system consisting of two hyperbolic periodic orbits with different dimensions of their unstable manifolds and a pair of orbits that connect them. For systems which are at least…

Dynamical Systems · Mathematics 2024-04-11 Dongchen Li , Dmitry Turaev

The task of inducing, via continuous static state-feedback control, an asymptotically stable heteroclinic orbit in a nonlinear control system is considered in this paper. The main motivation comes from the problem of ensuring convergence to…

Systems and Control · Electrical Eng. & Systems 2023-02-16 Christian Fredrik Sætre , Anton S. Shiriaev