no code implementations • 2 Apr 2024 • Matteo Marchi, Stefano Soatto, Pratik Chaudhari, Paulo Tabuada
The aim of this paper is to provide insights into this process (that we refer to as "generative closed-loop learning") by studying the learning dynamics of generative models that are fed back their own produced content in addition to their original training dataset.
no code implementations • 29 May 2023 • Stefano Soatto, Paulo Tabuada, Pratik Chaudhari, Tian Yu Liu
We then characterize the subset of meanings that can be reached by the state of the LLMs for some input prompt, and show that a well-trained bot can reach any meaning albeit with small probability.
no code implementations • 9 Mar 2022 • Alimzhan Sultangazin, Luigi Pannocchi, Lucas Fraile, Paulo Tabuada
In this paper, we revisit the problem of learning a stabilizing controller from a finite number of demonstrations by an expert.
no code implementations • 25 Sep 2021 • Zexiang Liu, Tzanis Anevlavis, Necmiye Ozay, Paulo Tabuada
In this paper, we derive closed-form expressions for implicit controlled invariant sets for discrete-time controllable linear systems with measurable disturbances.
no code implementations • 17 Sep 2021 • Yanwen Mao, Paulo Tabuada
This motivates a 2-step solution to the decentralized secure state-tracking problem: (1) each node tracks the compressed version of all the network measurements, and (2) each node asymptotically reconstructs the state from the output of step (1).
no code implementations • 17 Feb 2021 • Jonathan Bunton, Paulo Tabuada
In model selection problems for machine learning, the desire for a well-performing model with meaningful structure is typically expressed through a regularized optimization problem.
no code implementations • 6 Jan 2021 • Yanwen Mao, Aritra Mitra, Shreyas Sundaram, Paulo Tabuada
To better understand this, we show that when the $\mathbf{A}$ matrix of the linear system has unitary geometric multiplicity, the gap disappears, i. e., eigenvalue observability coincides with sparse observability, and there exists a polynomial time algorithm to reconstruct the state provided the state can be reconstructed.
no code implementations • ICLR 2021 • Paulo Tabuada, Bahman Gharesifard
In this paper, we explain the universal approximation capabilities of deep residual neural networks through geometric nonlinear control.
no code implementations • 30 Mar 2020 • Lucas Fraile, Matteo Marchi, Paulo Tabuada
In this paper we propose a methodology for stabilizing single-input single-output feedback linearizable systems when no system model is known and no prior data is available to identify a model.
1 code implementation • 7 Sep 2018 • Andreea B. Alexandru, Konstantinos Gatsis, Yasser Shoukry, Sanjit A. Seshia, Paulo Tabuada, George J. Pappas
The development of large-scale distributed control systems has led to the outsourcing of costly computations to cloud-computing platforms, as well as to concerns about privacy of the collected sensitive data.
Optimization and Control Cryptography and Security Systems and Control
1 code implementation • 30 Oct 2015 • Paulo Tabuada, Daniel Neider
Although it is widely accepted that every system should be robust, in the sense that "small" violations of environment assumptions should lead to "small" violations of system guarantees, it is less clear how to make this intuitive notion of robustness mathematically precise.
Logic in Computer Science Systems and Control Optimization and Control 03B44 F.4.1