Ensemble learning improves classification performance by combining multiple base classifiers. While increasing the number of classifiers generally enhances accuracy, excessively large ensembles can lead to computational inefficiency and diminishing returns. This paper investigates the relationship between ensemble size and performance through the lens of linear independence among classifier votes in data streams. We propose that ensembles composed of linearly independent classifiers maximize representational capacity, particularly under a geometric model. We then generalize the importance of linear independence to the weighted majority voting problem. By modeling the probability of achieving linear independence among classifier outputs, we derive a theoretical framework that explains the trade-off between ensemble size and accuracy. Our analysis leads to a theoretical estimate of the ensemble size required to achieve a user-specified probability of linear independence. We validate our theory through experiments on both real-world and synthetic datasets using two ensemble methods, OzaBagging and GOOWE. Our results confirm that this theoretical estimate effectively identifies the point of performance saturation for robust ensembles like OzaBagging. Conversely, for complex weighting schemes like GOOWE, our framework reveals that high theoretical diversity can trigger algorithmic instability. Our implementation is publicly available to support reproducibility and future research.

Online sparse linear regression is the task of applying linear regression analysis to examples arriving sequentially subject to a resource constraint that a limited number of features of examples can be observed. Despite its importance in many practical applications, it has been recently shown that there is no polynomial-time sublinear-regret algorithm unless NP BPP, and only an exponential-time sublinear-regret algorithm has been found. In this paper, we introduce mild assumptions to solve the problem.

We analyze linear independence of rank one tensors produced by tensor powers of randomly perturbed vectors. This enables efficient decomposition of sums of high-order tensors. Our analysis builds upon Bhaskara et al.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper considers transfer learning in a multi-armed bandit setting. The model considered has a sequence of episodes, and in each episode, the vector of distributions (one for each arm) is drawn iid from a discrete distribution. In this setting, it is possible to exploit history to learn what this discrete distribution is, and to use this information to reduce regret in each episode. An algorithm is proposed that does this, and cumulative regret bounds are shown for this algorithm.

On validation data minimize the loss l over class G to obtain f = g ˆ f . Solve the optimization problem (5) using f to get null w . Our experiments follow Alexandari et al. Covariate shift is well explored in past [28, 27, 7, 6, 9]. Approaches for estimating label shift (or prior shift) can be categorized into three classes: 1.

Dimensionality reduction can distort vector space properties such as orthogonality and linear independence, which are critical for tasks including cross-modal retrieval, clustering, and classification. We propose a Relationship Preserving Loss (RPL), a loss function that preserves these properties by minimizing discrepancies between relationship matrices (e.g., Gram or cosine) of high-dimensional data and their low-dimensional embeddings. RPL trains neural networks for non-linear projections and is supported by error bounds derived from matrix perturbation theory. Initial experiments suggest that RPL reduces embedding dimensions while largely retaining performance on downstream tasks, likely due to its preservation of key vector space properties. While we describe here the use of RPL in dimensionality reduction, this loss can also be applied more broadly, for example to cross-domain alignment and transfer learning, knowledge distillation, fairness and invariance, dehubbing, graph and manifold learning, and federated learning, where distributed embeddings must remain geometrically consistent.

Controlled ordinary differential equations driven by continuous bounded variation curves can be considered a continuous time analogue of recurrent neural networks for the construction of expressive features of the input curves. We ask up to which extent well known signature features of such curves can be reconstructed from controlled ordinary differential equations with (untrained) random vector fields. The answer turns out to be algebraically involved, but essentially the number of signature features, which can be reconstructed from the non-linear flow of the controlled ordinary differential equation, is exponential in its hidden dimension, when the vector fields are chosen to be neural with depth two. Moreover, we characterize a general linear independence condition on arbitrary vector fields, under which the signature features up to some fixed order can always be reconstructed. Algebraically speaking this complements in a quantitative manner several well known results from the theory of Lie algebras of vector fields and puts them in a context of machine learning.

In recent years, deep learning, powered by neural networks, has achieved widespread success in solving high-dimensional problems, particularly those with low-dimensional feature structures. This success stems from their ability to identify and learn low dimensional features tailored to the problems. Understanding how neural networks extract such features during training dynamics remains a fundamental question in deep learning theory. In this work, we propose a novel perspective by interpreting the neurons in the last hidden layer of a neural network as basis functions that represent essential features. To explore the linear independence of these basis functions throughout the deep learning dynamics, we introduce the concept of 'effective rank'. Our extensive numerical experiments reveal a notable phenomenon: the effective rank increases progressively during the learning process, exhibiting a staircase-like pattern, while the loss function concurrently decreases as the effective rank rises. We refer to this observation as the 'staircase phenomenon'. Specifically, for deep neural networks, we rigorously prove the negative correlation between the loss function and effective rank, demonstrating that the lower bound of the loss function decreases with increasing effective rank. Therefore, to achieve a rapid descent of the loss function, it is critical to promote the swift growth of effective rank. Ultimately, we evaluate existing advanced learning methodologies and find that these approaches can quickly achieve a higher effective rank, thereby avoiding redundant staircase processes and accelerating the rapid decline of the loss function.

Online sparse linear regression is the task of applying linear regression analysis to examples arriving sequentially subject to a resource constraint that a limited number of features of examples can be observed. Despite its importance in many practical applications, it has been recently shown that there is no polynomialtime sublinear-regret algorithm unless NP BPP, and only an exponential-time sublinear-regret algorithm has been found. In this paper, we introduce mild assumptions to solve the problem.