AI Theory

This paper introduces a novel framework for learning discrete concepts from high-dimensional data, establishing theoretical conditions for identifying underlying hierarchical causal structures and pro…

JKOnet* learns diffusion processes at unprecedented speed and accuracy by directly minimizing a simple quadratic loss function, bypassing complex bilevel optimization problems.

This research develops data-driven methods for selecting optimal cut generating functions in integer programming, providing theoretical guarantees and empirical improvements over existing techniques.

NeuRes, a novel neuro-symbolic approach, achieves superior SAT solving accuracy using significantly less training data than existing methods by combining certificate-driven learning with expert iterat…

This work presents a computationally efficient algorithm that robustly learns a single neuron despite adversarial label noise and distributional shifts, providing provable approximation guarantees.

Two-parameter models can surprisingly learn high-dimensional targets with near-perfect accuracy using gradient flow, challenging the need for high-dimensional models.

Latent Neural Operator (LNO) dramatically improves solving PDEs by using a latent space, boosting accuracy and reducing computation costs.

Generalized Frank-Wolfe algorithm achieves fast last-iterate convergence for constrained monotone variational inequalities, even with noisy data.

Langevin unlearning offers a novel, privacy-preserving machine unlearning framework based on noisy gradient descent, handling both convex and non-convex problems efficiently.

Faster John ellipsoid computation achieved via lazy updates and fast matrix multiplication, improving efficiency and enabling low-space streaming algorithms.

This paper proposes a novel framework, the locally evolving set process, to develop faster localized iterative methods for solving large-scale graph problems, achieving significant speedup over existi…

Weighted score matching offers a consistent, efficient solution for estimating parameters in point processes, overcoming the limitations of previous methods.

Zero Graves-Lai constant ensures both bounded regret and delay robustness in online decision-making, particularly for linear models.

In strategic settings, repeated interactions alone may not enable uninformed players to achieve optimal outcomes, highlighting the persistent impact of information asymmetry.

Cross-validation isn’t always superior; simple plug-in methods often perform equally well for estimating out-of-sample model performance, especially when considering computational costs.

IPM-LSTM accelerates nonlinear program solving by up to 70% using LSTM networks to approximate linear system solutions within the interior point method.

Generalized eigenvalue problems get solved in nearly matrix multiplication time, providing new, faster PCA algorithms!

Researchers unveil text-level graph injection attacks, revealing a new vulnerability in GNNs and highlighting the importance of text interpretability in attack success.

Strategic players can manipulate reward signals, but simple threshold policies still achieve a surprisingly good approximation to the optimal prophet value, even in this more realistic setting.

This paper introduces a novel framework for creating interventionally consistent surrogate models for complex simulations, addressing computational limitations and ensuring accurate policy evaluation.