Related papers: DL-DDA -- Deep Learning based Dynamic Difficulty A…
To perform well, Deep Reinforcement Learning (DRL) methods require significant memory resources and computational time. Also, sometimes these systems need additional environment information to achieve a good reward. However, it is more…
We consider the problem of searching an input maximizing a black-box objective function given a static dataset of input-output queries. A popular approach to solving this problem is maintaining a proxy model, e.g., a deep neural network…
Unsupervised domain adaptation (UDA) aims to improve the classification performance on an unlabeled target domain by leveraging information from a fully labeled source domain. Recent approaches explore domain-invariant and…
Reinforcement learning has become a cornerstone technique for developing reasoning models in complex tasks, ranging from mathematical problem-solving to imaginary reasoning. The optimization of these models typically relies on policy…
Owe to the recent advancements in Artificial Intelligence especially deep learning, many data-driven decision support systems have been implemented to facilitate medical doctors in delivering personalized care. We focus on the deep…
Dynamic complexity is concerned with updating the output of a problem when the input is slightly changed. We study the dynamic complexity of two-player parity games over graphs of bounded tree-width, where updates may add or delete edges,…
Consider a strongly monotone game where the players' utility functions include a reward function and a linear term for each dimension, with coefficients that are controlled by the manager. Gradient play converges to a unique Nash…
Targeted interventions in games present a challenging problem due to the asymmetric information available to the regulator and the agents. This note addresses the problem of steering the actions of self-interested agents in quadratic…
Domain adaptation (DA) aims at improving the performance of a model on target domains by transferring the knowledge contained in different but related source domains. With recent advances in deep learning models which are extremely data…
Despite dropout's ubiquity in machine learning, its effectiveness as a form of data augmentation remains under-explored. We address two key questions: (i) When is dropout effective as an augmentation strategy? (ii) Is dropout uniquely…
Adversarial images are designed to mislead deep neural networks (DNNs), attracting great attention in recent years. Although several defense strategies achieved encouraging robustness against adversarial samples, most of them fail to…
There is a growing interest in researching game design processes, artifacts and culture through active game design. Tools and processes to support these attempts are limited, especially in terms of a) capturing smaller design decisions…
Discriminative features play an important role in image and object classification and also in other fields of research such as semi-supervised learning, fine-grained classification, out of distribution detection. Inspired by Linear…
In recent years, one of the most popular techniques in the computer vision community has been the deep learning technique. As a data-driven technique, deep model requires enormous amounts of accurately labelled training data, which is often…
Deep neural networks are vulnerable to adversarial examples. Adversarial training (AT) is an effective defense against adversarial examples. However, AT is prone to overfitting which degrades robustness substantially. Recently, data…
Deep neural networks are typically trained by uniformly sampling large datasets across epochs, despite evidence that not all samples contribute equally throughout learning. Recent work shows that progressively reducing the amount of…
Quantization is a technique for reducing deep neural networks (DNNs) training and inference times, which is crucial for training in resource constrained environments or applications where inference is time critical. State-of-the-art (SOTA)…
We introduce Deep Adaptive Design (DAD), a method for amortizing the cost of adaptive Bayesian experimental design that allows experiments to be run in real-time. Traditional sequential Bayesian optimal experimental design approaches…
Most games have, or can be generalised to have, a number of parameters that may be varied in order to provide instances of games that lead to very different player experiences. The space of possible parameter settings can be seen as a…
We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…