Related papers: Cross-training with Imperfect training Schemes
Cross-validation is a common method for estimating the predictive performance of machine learning models. In a data-scarce regime, where one typically wishes to maximize the number of instances used for training the model, an approach…
Working becomes harder as we grow tired or bored. I model individuals who underestimate these changes in marginal disutility -- as implied by "projection bias" -- when deciding whether or not to continue working. This bias causes people's…
Efficient job-shop scheduling with transportation resources is critical for high-performance manufacturing. With the rise of "decentralized factories", multi-agent reinforcement learning has emerged as a promising approach for the combined…
Background: Multitasking is usual in software development. It is the ability to stop working on a task, switch to another, and return eventually to the first one, as needed or as scheduled. Multitasking, however, comes at a cognitive cost:…
Loading models pre-trained on the large-scale corpus in the general domain and fine-tuning them on specific downstream tasks is gradually becoming a paradigm in Natural Language Processing. Previous investigations prove that introducing a…
Disagreement-based approaches generate multiple classifiers and exploit the disagreement among them with unlabeled data to improve learning performance. Co-training is a representative paradigm of them, which trains two classifiers…
Measuring Efficiency in neural network system development is an open research problem. This paper presents an experimental framework to measure the training efficiency of a neural architecture. To demonstrate our approach, we analyze the…
State-of-the-art cross-encoders can be fine-tuned to be highly effective in passage re-ranking. The typical fine-tuning process of cross-encoders as re-rankers requires large amounts of manually labelled data, a contrastive learning…
Shift planning plays a key role for the health and well-being of healthcare workers. It determines when they work and when they can take time off to recover or engage in social activities. Current computer-support in shift planning is…
Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strategies for scoring item difficulty rely on indirect proxy…
Being able to solve a task in diverse ways makes agents more robust to task variations and less prone to local optima. In this context, constrained diversity optimization has become a useful reinforcement learning (RL) framework for…
Pre-training datasets are critical for building state-of-the-art machine learning models, motivating rigorous study on their impact on downstream tasks. In this work, we study the impact of the trade-off between the intra-class diversity…
How do people decide how long to continue in a task, when to switch, and to which other task? Understanding the mechanisms that underpin task interleaving is a long-standing goal in the cognitive sciences. Prior work suggests greedy…
Experimental evidence confirms that AI tools raise worker productivity, but also that sustained use can erode the expertise on which those gains depend. We develop a dynamic model in which a decision-maker chooses AI usage intensity for a…
Scrum teams are at the heart of the Scrum framework. Nevertheless, an integrated and systemic theory that can explain what makes some Scrum teams more effective than others is still missing. To address this gap, we performed a…
Trainable activation functions, whose parameters are optimized alongside network weights, offer increased expressivity compared to fixed activation functions. Specifically, trainable activation functions defined as ratios of polynomials…
There is no doubt that management practices are linked to the productivity and performance of a company. However, research findings are mixed. This paper provides a multi-disciplinary review of the current evidence of such a relationship…
In the context of decision making under explorable uncertainty, scheduling with testing is a powerful technique used in the management of computer systems to improve performance via better job-dispatching decisions. Upon job arrival, a…
Hardware compute power has been growing at an unprecedented rate in recent years. The utilization of such advancements plays a key role in producing better results in less time -- both in academia and industry. However, merging the existing…
This work examines the economic benefits of learning a new skill from a different domain: cross-skilling. To assess this, a network of skills from the job profiles of 14,790 online freelancers is constructed. Based on this skill network,…