arXiv research

Polynomial-time reachability for LTI systems with TLL NN controllers is achieved.

Verifying correctness of deep neural networks (DNNs) is challenging. We study a generic reachability problem for feed-forward DNNs which, for a given set of inputs to the network and a Lipschitz-continuous function over its outputs, computes the lower and upper bound on the function values. Because the network and the …

Deep learning method proves convergence for solving HJI equations.

Study analyzes and enhances robustness of neural networks for classification and regression.

We quantify content availability and user discovery opportunities in recommender systems.

Lumbermark clusters data robustly, slicing limbs of mutual reachability trees.

Guaranteed reachable set for unknown nonlinear systems on manifolds.

Improves data-driven reachability estimation for complex systems.

This paper tackles data-efficient nonlinear control in Hamiltonian systems using symplectic geometry.

Safe imitation learning with a safety layer for flexible training.

GraphReach improves GNN performance by incorporating node positions.

Study on Heisenberg group's Lorentzian problems using Pontryagin's principle.

CIfly simplifies causal inference tasks with linear-time reachability primitives.

Procedure verifies if machine learning models assign fixed predictions that preclude access.

Study of 2D Lorentzian anti-de Sitter plane using geometric control theory.

GoTube verifies neural networks over time, scaling to large horizons.

Quantum neural networks need both data-dependent and trainable unitaries for effective geometric deformation.

Compact reachability embeddings for hierarchical data

We address the problem of verifying neural-based perception systems implemented by convolutional neural networks. We define a notion of local robustness based on affine and photometric transformations. We show the notion cannot be captured by previously employed notions of robustness. The method proposed is based on re…

Influence maximization (IM) is the problem of finding for a given $s\geq 1$ a set $S$ of $|S|=s$ nodes in a network with maximum influence. With stochastic diffusion models, the influence of a set $S$ of seed nodes is defined as the expectation of its reachability over simulations, where each simulation specifies a det…

A new clustering algorithm considers data smoothness for better performance.

Deep neural networks are widely used for nonlinear function approximation with applications ranging from computer vision to control. Although these networks involve the composition of simple arithmetic operations, it can be very challenging to verify whether a particular network satisfies certain input-output propertie…

ViTaX provides formal guarantees for targeted explanations in safety-critical systems.

DARLING tackles non-stationary RL with guarantees, improving dynamic regret.

CAST improves spectral clustering for multi-scale data by integrating reachability similarity.

Recommender systems often rely on models which are trained to maximize accuracy in predicting user preferences. When the systems are deployed, these models determine the availability of content and information to different users. The gap between these objectives gives rise to a potential for unintended consequences, co…

Improved exploration algorithm for unknown MDPs with reduced sample complexity.

How can we design safe reinforcement learning agents that avoid unnecessary disruptions to their environment? We show that current approaches to penalizing side effects can introduce bad incentives, e.g. to prevent any irreversible changes in the environment, including the actions of other agents. To isolate the source…

In finance industry portfolio construction deals with how to divide the investors' wealth across an asset-classes' menu in order to maximize the investors' gain. Main approaches in use at the present are based on variations of the classical Markowitz model. However, recent evolutions of the world market showed limitati…

New distances for causal graphs improve evaluation of learned structures.

We construct normal forms for Lorentzian metrics on Engel distributions under the assumption that abnormal curves are timelike future directed Hamiltonian geodesics. Then we indicate some cases in which the abnormal timelike future directed curve initiating at the origin is geometrically optimal. We also give certain e…

In classical reinforcement learning, when exploring an environment, agents accept arbitrary short term loss for long term gain. This is infeasible for safety critical applications, such as robotics, where even a single unsafe action may cause system failure. In this paper, we address the problem of safely exploring fin…

CUDC collects diverse data for offline RL by predicting future states.

Improves RL from historical data by stitching trajectories.

We consider examples of the $\mathbb H$-type groups with the natural horizontal distribution generated by the commutation relations of the group. In the contrast with the previous studies we furnish the horizontal distribution with the Lorentzian metric, which is nondegenerate metric of index 1 instead of a positive de…

C-Learning estimates reachability over time to solve multi-goal tasks.

In this paper we approach two relevant deep learning topics: i) tackling of graph structured input data and ii) a better understanding and analysis of deep networks and related learning algorithms. With this in mind we focus on the topological classification of reachability in a particular subset of planar graphs (Maze…

Estimates convex hulls of smooth function images with error bounds.

Study improves understanding of why agentic theorem provers succeed.

The paper certifies neural network-based control barrier functions efficiently.

We prove a lower bound for feature dimension in linear MDPs and propose a novel dynamics aggregation framework.

New Q-learning method achieves optimal sample complexity for average-reward problems.

CANs improve GANs by enforcing structured constraints during training.

While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and position contains configurations that are not physically reachable). This leads to defining weakly-communicating or multi-chain MDPs. In this…

Active sampling selects few points for accurate model reduction of high-fidelity systems.

Framework for dynamic node embeddings from graph streams.

ProGraML uses graph-based machine learning to improve program optimization and analysis.

Physics-informed GCRL tackles sparse feedback learning with hybrid dynamics.