Related papers: A note on the capability profile - localized incre…

Tis paper is a literature review focusing on human capital, skills of employees, demographic change, management, training and their impact on productivity growth. Intrafirm behaviour has been recognized as a potentially important driver for…

This paper is concerned with introducing a framework in which the operational effectiveness of a dismounted combat team can be assessed. It has been motivated by studies at Defence Science and Technology Group which have focused on the…

We use a formal correspondence between thermodynamics and inference, where the number of samples can be thought of as the inverse temperature, to study a quantity called ``learning capacity'' which is a measure of the effective…

A multiplicative effects model is introduced for the identification of the factors that are influential to the performance of highly-trained endurance runners. The model extends the established power-law relationship between performance…

The efficacy of deep learning models has been called into question by the presence of adversarial examples. Addressing the vulnerability of deep learning models to adversarial examples is crucial for ensuring their continued development and…

Rehearsal is one of the key techniques for mitigating catastrophic forgetting and has been widely adopted in continual learning algorithms due to its simplicity and practicality. However, the theoretical understanding of how rehearsal scale…

Topological loss based on persistent homology has shown promise in various applications. A topological loss enforces the model to achieve certain desired topological property. Despite its empirical success, less is known about the…

Recent studies show that task distribution plays a vital role in the meta-learner's performance. Conventional wisdom is that task diversity should improve the performance of meta-learning. In this work, we find evidence to the contrary; (i)…

Constrained reinforcement learning is to maximize the expected reward subject to constraints on utilities/costs. However, the training environment may not be the same as the test one, due to, e.g., modeling error, adversarial attack,…

We identify an issue in multi-task learnable compression, in which a representation learned for one task does not positively contribute to the rate-distortion performance of a different task as much as expected, given the estimated amount…

Existing works have shown that fine-tuned textual transformer models achieve state-of-the-art prediction performances but are also vulnerable to adversarial text perturbations. Traditional adversarial evaluation is often done \textit{only…

Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions. This seemingly implies that high-performing models share similar biases regardless of training…

Modern foundation models often undergo iterative ``bootstrapping'' in their post-training phase: a model generates synthetic data, an external verifier filters out low-quality samples, and the high-quality subset is used for further…

Structural models that admit multiple reduced forms, such as game-theoretic models with multiple equilibria, pose challenges in practice, especially when parameters are set-identified and the identified set is large. In such cases,…

Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition. The same philosophy…

Independently trained machine learning models tend to learn similar features. Given an ensemble of independently trained models, this results in correlated predictions and common failure modes. Previous attempts focusing on decorrelation of…

Evaluating different training interventions to determine which produce the best learning outcomes is one of the main challenges faced by instructional designers. Typically, these designers use A/B experiments to evaluate each intervention;…

This study delves into the origins of excess capacity by examining the reactions of capital, labor, and capital intensity. To achieve this, we have employed a novel three-layered production function model, estimating the elasticity of…

We introduce a metric for evaluating the robustness of a classifier, with particular attention to adversarial perturbations, in terms of expected functionality with respect to possible adversarial perturbations. A classifier is assumed to…

Performance-critical machine learning models should be robust to input perturbations not seen during training. Adversarial training is a method for improving a model's robustness to some perturbations by including them in the training…