Related papers: Denoised MDPs: Learning World Models Better Than t…
In this thesis we aim to analyze and quantify the energetic and information contents that can be extracted from a dynamical system subject to the external environment. The latter is usually assumed to be deleterious for the feasibility of…
Communication is essential for coordination among humans and animals. Therefore, with the introduction of intelligent agents into the world, agent-to-agent and agent-to-human communication becomes necessary. In this paper, we first study…
Noise is a fundamental problem in learning theory with huge effects in the application of Machine Learning (ML) methods, due to real world data tendency to be noisy. Additionally, introduction of malicious noise can make ML methods fail…
This work is motivated by a question at the heart of unsupervised learning approaches: Assume we are collecting a number K of (subjective) opinions about some event E from K different agents. Can we infer E from them? Prima facie this seems…
Certified machine unlearning aims to provably remove the influence of a deletion set $U$ from a model trained on a dataset $S$, by producing an unlearned output that is statistically indistinguishable from retraining on the retain set…
In this dissertation, we propose a systemic framework that prioritizes informative features and examples to enhance each stage of the development process. Specifically, we prioritize informative features and examples and improve the…
With its significant performance improvements, the deep learning paradigm has become a standard tool for modern image denoisers. While promising performance has been shown on seen noise distributions, existing approaches often suffer from…
General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes…
The denoising of magnetic resonance (MR) images is a task of great importance for improving the acquired image quality. Many methods have been proposed in the literature to retrieve noise free images with good performances. Howerever, the…
Iterative self-training (self-distillation) repeatedly refits a model on pseudo-labels generated by its own predictions. We study this procedure in overparameterized linear regression: an initial estimator is trained on noisy labels, and…
Pre-trained LMs have shown impressive performance on downstream NLP tasks, but we have yet to establish a clear understanding of their sophistication when it comes to processing, retaining, and applying information presented in their input.…
World models have been recently proposed as sandbox environments in which AI agents can be trained and evaluated before deployment. While realistic world models often have high computational demands, this can often be alleviated by…
The problem of learning in the absence of external intelligence is discussed in the context of a simple model. The model consists of a set of randomly connected, or layered integrate-and fire neurons. Inputs to and outputs from the…
Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly…
Despite their outstanding performance in a broad spectrum of real-world tasks, deep artificial neural networks are sensitive to input noises, particularly adversarial perturbations. On the contrary, human and animal brains are much less…
Noise, traditionally considered a nuisance in computational systems, is reconsidered for its unexpected and counter-intuitive benefits across a wide spectrum of domains, including nonlinear information processing, signal processing, image…
We develop model free PAC performance guarantees for multiple concurrent MDPs, extending recent works where a single learner interacts with multiple non-interacting agents in a noise free environment. Our framework allows noisy and resource…
Machine unlearning aims to remove the influence of specific training data from a model without requiring full retraining. This capability is crucial for ensuring privacy, safety, and regulatory compliance. Therefore, verifying whether a…
Humans and animals explore their environment and acquire useful skills even in the absence of clear goals, exhibiting intrinsic motivation. The study of intrinsic motivation in artificial agents is concerned with the following question:…
Dynamic scheduling is an important problem in applications from queuing to wireless networks. It addresses how to choose an item among multiple scheduling items in each timestep to achieve a long-term goal. Conventional approaches for…