Related papers: The cerebellum could solve the motor error problem…
We develop many-server asymptotics in the QED regime for models with admission control. The admission control, designed to reduce the incoming traffic in periods of congestion, scales with the size of the system. For a class of Markovian…
A common view on the brain learning processes proposes that the three classic learning paradigms -- unsupervised, reinforcement, and supervised -- take place in respectively the cortex, the basal-ganglia, and the cerebellum. However,…
Based on existing data, we wish to put forward a biological model of motor system on the neuron scale. Then we indicate its implications in statistics and learning. Specifically, neuron firing frequency and synaptic strength are probability…
The primal-dual hybrid gradient (PDHG) method is one of the most popular algorithms for solving saddle point problems. However, when applying the PDHG method and its many variants to some real-world models commonly encountered in signal…
Min-max optimization problems, also known as saddle point problems, have attracted significant attention due to their applications in various fields, such as fair beamforming, generative adversarial networks (GANs), and adversarial…
Designing neural network architectures is a challenging task and knowing which specific layers of a model must be adapted to improve the performance is almost a mystery. In this paper, we introduce a novel theory and metric to identify…
Model Predictive Controllers (MPC) require a good model for the controlled process. In this paper I infer inductive biases about a physical system. I use these biases to derive a new neural network architecture that can model this real…
Many real-world control problems involve both discrete decision variables - such as the choice of control modes, gear switching or digital outputs - as well as continuous decision variables - such as velocity setpoints, control gains or…
Retrieval-augmented LLMs are deployed for tasks where evidence quality determines action safety, yet evaluation protocols assume that single-turn robustness predicts robustness when evidence accumulates across turns. We show this assumption…
We present an architecture where a feedback controller derived on an approximate model of the environment assists the learning process to enhance its data efficiency. This architecture, which we term as Control-Tutored Q-learning (CTQL), is…
We propose a hybrid model predictive control algorithm, consensus complementarity control (C3), for systems that make and break contact with their environment. Many state-of-the-art controllers for tasks which require initiating contact…
We address the problem of learning to control an unknown nonlinear dynamical system through sequential interactions. Motivated by high-stakes applications in which mistakes can be catastrophic, such as robotics and healthcare, we study…
Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…
A sequence-to-sequence model is a neural network module for mapping two sequences of different lengths. The sequence-to-sequence model has three core modules: encoder, decoder, and attention. Attention is the bridge that connects the…
Understanding how movement is controlled by the central nervous system remains a major challenge, with ongoing debate about basic features underlying this control. In this review, we introduce a new conceptual framework for the distribution…
A fundamental problem in neuroscience is to understand how sequences of action potentials ("spikes") encode information about sensory signals and motor outputs. Although traditional theories of neural coding assume that information is…
We propose an approach to saddle point optimization relying only on oracles that solve minimization problems approximately. We analyze its convergence property on a strongly convex--concave problem and show its linear convergence toward the…
Synaptic connections are known to change dynamically. High-frequency presynaptic inputs induce decrease of synaptic weights. This process is known as short-term synaptic depression. The synaptic depression controls a gain for presynaptic…
An iterative learning algorithm is presented for continuous-time linear-quadratic optimal control problems where the system is externally symmetric with unknown dynamics. Both finite-horizon and infinite-horizon problems are considered. It…
Metacognition is the concept of reasoning about an agent's own internal processes, and it has recently received renewed attention with respect to artificial intelligence (AI) and, more specifically, machine learning systems. This paper…