AI Theory

AI learns to compute Gröbner bases, solving a notorious computational algebra problem efficiently via Transformers and novel algebraic techniques.

A novel Common-Points-Picking algorithm efficiently learns stable reward allocations (expected core) in strictly convex stochastic cooperative games with unknown reward distributions, achieving high p…

This research pioneers the integration of machine learning with the dependently-typed programming language Agda, introducing a novel dataset and neural architecture for faithful program representation…

Learning social welfare functions from past decisions is possible! This paper shows how to efficiently learn power mean functions, a widely used family, using both cardinal and pairwise welfare compar…

Learn graph representations efficiently by identifying the minimal data needed to uniquely define a graph’s structure, achieving robust performance with fewer resources.

CryptoANFNet accelerates solving cryptographic problems by 50x using a novel graph neural network and ANF representation, outperforming existing methods in accuracy.

Neural networks learn place cell-like representations and context-dependent remapping using a novel similarity-based objective function, providing insights into hippocampal encoding.

Learning hidden structures from sparse interactions in data is computationally hard but can be achieved with sufficient samples using gradient-based methods; This is shown by analyzing the gradient dy…

AI learns optimal taxes for congestion games, maximizing social welfare with limited feedback, via a novel algorithm.

ELCD: The first neural network guaranteeing globally contracting dynamics!

Researchers developed an efficient algorithm to uniquely identify causal relationships from mixed interventional and observational data with noisy interventions.

LiNGCREL, a novel algorithm, provably recovers linear causal representations from diverse environments, achieving identifiability despite intrinsic ambiguities, thus advancing causal AI.

FCR, a novel method, reveals causal structure in single-cell perturbation data by learning disentangled cellular representations specific to covariates, treatments, and their interactions, outperformi…

Aligning AI’s world representation with humans enables faster, safer learning of human values, improving both exploration and generalization.

Learn optimal LP values faster with a novel neural network method!

ZORRO: A new method for learning linear models from uncertain data, providing sound over-approximations of all possible models and prediction ranges.

This paper presents novel theoretical frameworks and algorithms for learning from snapshots of discrete and continuous data streams, resolving key learnability challenges in online learning under cont…

Learn optimal transport maps with structured displacements using elastic costs and a novel bilevel loss function!

AI learns emergent system features from time-series data using a novel differentiable architecture maximizing causal emergence, outperforming pure mutual information maximization.

This paper introduces a novel tensor rank condition for identifying causal structures among discrete latent variables, advancing causal discovery in complex scenarios.