Supervised classification techniques use training samples to find classification ruleswithsmallexpected0-1loss.

In the following, we respond to all the reviewers' questions that will be addressed in the paper's final version together W e would also like to point out t hat the bounds' tightness is shown not only in Fig.1 but However, as the Reviewer ment ions, the paper offers new insights for feature mappings' Those with large number of samples were used for co mparison with performance bounds in Fig.1 over one Theorem 1. Infinite instance spaces would require to use heav ier tools from variational analysis in such proof, but the

Supervised classification techniques use training samples to find classification rules with small expected 0-1 loss. Conventional methods achieve efficient learning and out-of-sample generalization by minimizing surrogate losses over specific families of rules. This paper presents minimax risk classifiers (MRCs) that do not rely on a choice of surrogate loss and family of rules. MRCs achieve efficient learning and out-of-sample generalization by minimizing worst-case expected 0-1 loss w.r.t.

Supervised learning with large-scale data usually leads to complex optimization problems, especially for classification tasks with multiple classes. Stochastic subgradient methods can enable efficient learning with a large number of samples for classification techniques that minimize the average loss over the training samples. However, recent techniques, such as minimax risk classifiers (MRCs), minimize the maximum expected loss and are not amenable to stochastic subgradient methods. In this paper, we present a learning algorithm based on the combination of constraint and column generation that enables efficient learning of MRCs with large-scale data for classification tasks with multiple classes. Experiments on multiple benchmark datasets show that the proposed algorithm provides upto a 10x speedup for general large-scale data and around a 100x speedup with a sizeable number of classes.

Language fairness in multilingual information retrieval (MLIR) systems is crucial for ensuring equitable access to information across diverse languages. This paper sheds light on the issue, based on the assumption that queries in different languages, but with identical semantics, should yield equivalent ranking lists when retrieving on the same multilingual documents. We evaluate the degree of fairness using both traditional retrieval methods, and a DPR neural ranker based on mBERT and XLM-R. Additionally, we introduce `LaKDA', a novel loss designed to mitigate language biases in neural MLIR approaches. Our analysis exposes intrinsic language biases in current MLIR technologies, with notable disparities across the retrieval methods, and the effectiveness of LaKDA in enhancing language fairness.

-- The musculoskeletal humanoid can move well under environmental contact thanks to its body softness. However, there are few studies that actively make use of the environment to rest its flexible musculoskeletal body. Also, its complex musculoskeletal structure is difficult to modelize and high internal muscle tension sometimes occurs. T o solve these problems, we develop a muscle relaxation control which can minimize the muscle tension by actively using the environment and inhibit useless internal muscle tension. We apply this control to some basic movements, the motion of resting the arms on the desk, and handle operation, and verify its effectiveness. I. INTRODUCTION The musculoskeletal humanoid [1]-[4] has many biomimetic benefits such as muscle redundancy, variable stiffness control using nonlinear elastic elements, ball joints without extreme points, and the under-actuated fingers and spine.

Supervised classification techniques use training samples to find classification rules with small expected 0-1 loss. Conventional methods achieve efficient learning and out-of-sample generalization by minimizing surrogate losses over specific families of rules. This paper presents minimax risk classifiers (MRCs) that do not rely on a choice of surrogate loss and family of rules. MRCs achieve efficient learning and out-of-sample generalization by minimizing worst-case expected 0-1 loss w.r.t. In addition, MRCs' learning stage provides performance guarantees as lower and upper tight bounds for expected 0-1 loss.

Echo state property (ESP) is a fundamental property that allows an input-driven dynamical system to perform information processing tasks. Recently, extensions of ESP to potentially nonstationary systems and subsystems, that is, nonstationary ESP and subset/subspace ESP, have been proposed. In this paper, we theoretically and numerically analyze the sufficient and necessary conditions for a quantum system to satisfy nonstationary ESP and subset/subspace nonstationary ESP. Based on extensive usage of the Pauli transfer matrix (PTM) form, we find that (1) the interaction with a quantum-coherent environment, termed \textit{coherence influx}, is indispensable in realizing nonstationary ESP, and (2) the spectral radius of PTM can characterize the fading memory property of quantum reservoir computing (QRC). Our numerical experiment, involving a system with a Hamiltonian that entails a spin-glass/many-body localization phase, reveals that the spectral radius of PTM can describe the dynamical phase transition intrinsic to such a system. To comprehensively understand the mechanisms under ESP of QRC, we propose a simplified model, multiplicative reservoir computing (mRC), which is a reservoir computing (RC) system with a one-dimensional multiplicative input. Theoretically and numerically, we show that the parameters corresponding to the spectral radius and coherence influx in mRC directly correlates with its linear memory capacity (MC). Our findings about QRC and mRC will provide a theoretical aspect of PTM and the input multiplicativity of QRC. The results will lead to a better understanding of QRC and information processing in open quantum systems.