Related papers: Do Projects Learn Across Space and Time? Evidence …

Machine learning algorithms can perform well when trained on large datasets. While large organisations often have considerable data assets, it can be difficult for these assets to be unified in a manner that makes training possible. Data is…

Deep learning have achieved promising results on a wide spectrum of AI applications. Larger datasets and models consistently yield better performance. However, we generally spend longer training time on more computation and communication.…

Inspired by human learning, researchers have proposed ordering examples during training based on their difficulty. Both curriculum learning, exposing a network to easier examples early in training, and anti-curriculum learning, showing the…

Hackathons are time-bounded collaborative events which have become a global phenomenon adopted by both researchers and practitioners in a plethora of contexts. Hackathon events are generally used to accelerate the development of, for…

Conventional theoretical machine learning studies generally assume explicitly or implicitly that there are enough or even infinitely supplied computational resources. In real practice, however, computational resources are usually limited,…

Optimizing the body and brain of a robot is a coupled challenge: the morphology determines what control strategies are effective, while the control parameters influence how well the morphology performs. This joint optimization can be done…

The spatial arrangement of individuals is thought to overcome the dilemma of cooperation: When cooperators engage in clusters they might share the benefit of cooperation while being more protected against non-cooperating individuals, which…

Spatial-temporal prediction is a fundamental problem for constructing smart city, which is useful for tasks such as traffic control, taxi dispatching, and environmental policy making. Due to data collection mechanism, it is common to see…

Navigation is one of the most heavily studied problems in robotics, and is conventionally approached as a geometric mapping and planning problem. However, real-world navigation presents a complex set of physical challenges that defies…

Decision making in modern large-scale and complex systems such as communication networks, smart electricity grids, and cyber-physical systems motivate novel game-theoretic approaches. This paper investigates big strategic (non-cooperative)…

Statistical learning theory provides the foundation to applied machine learning, and its various successful applications in computer vision, natural language processing and other scientific domains. The theory, however, does not take into…

In the field of robotics many different approaches ranging from classical planning over optimal control to reinforcement learning (RL) are developed and borrowed from other fields to achieve reliable control in diverse tasks. In order to…

Students of Computer Science often wonder when, exactly, one can apply a greedy algorithm to a problem, and when one must use the more complicated and time-consuming techniques of dynamic programming. This paper argues that the existing…

Continual learning systems operating in fixed-dimensional spaces face a fundamental geometric barrier: the flat manifold problem. When experience is represented as a linear trajectory in Euclidean space, the geodesic distance between…

The use of learned dynamics models, also known as world models, can improve the sample efficiency of reinforcement learning. Recent work suggests that the underlying causal graphs of such dynamics models are sparsely connected, with each of…

This paper extends endogenous economic growth models to incorporate knowledge externality. We explores whether spatial knowledge spillovers among regions exist, whether spatial knowledge spillovers promote regional innovative activities,…

About one fifth of Ph.D's across all STEM disciplines secure a tenure track position in academia. It is also the case that science and engineering have evolved significantly and so has the nature of the labor market and the increasingly…

In most practical settings and theoretical analyses, one assumes that a model can be trained until convergence. However, the growing complexity of machine learning datasets and models may violate such assumptions. Indeed, current approaches…

Westudy how a planner can design dynamic interventions to overcome status-quo inertia in living temporal games, where strategic agents control their state (active, sleep, partially dead) on a temporal network. Building on the…

Multi-objective combinatorial optimization seeks Pareto-optimal solutions over exponentially large discrete spaces, yet existing methods sacrifice generality, scalability, or theoretical guarantees. We reformulate it as an online learning…