AI Theory

New algorithms achieve optimal regret bounds for contextual dynamic pricing under minimal assumptions, improving revenue management with better price adjustments.

Weighted pretrained features implicitly regularize models, and this paper reveals equivalent paths between weighting schemes and ridge regularization, enabling efficient hyperparameter tuning.

Decentralized Gradient Descent achieves statistically optimal sparse model learning via implicit regularization, even with communication-efficient truncation.

Mirror descent’s implicit bias on separable data is formally characterized, revealing convergence towards a maximum margin classifier determined by the potential’s ‘horizon function’.

Proper weight initialization significantly boosts Graph Neural Network (GNN) and Deep Neural Network (DNN) robustness against adversarial attacks, highlighting a critical, often-overlooked factor.

Researchers can now pinpoint the sources of data shifts in complex linear causal systems using a new algorithm, even with limited perfect interventions, opening exciting possibilities for causal disco…

End-to-end sparse autoencoders revolutionize neural network interpretability by learning functionally important features, outperforming traditional methods in efficiency and accuracy.

New framework uses Koopman operator theory to identify equivalent training dynamics in deep neural networks, enabling quantitative comparison of different architectures and optimization methods.

Unlocking identifiability of causal effects: This paper leverages functional dependencies in causal graphs to improve identifiability, leading to fewer needed variables in observational data.

This paper proves that non-active exploration suffices for identifying linearly parameterized nonlinear systems with real-analytic features, providing non-asymptotic guarantees for least-squares and s…

PReBiM algorithm accurately estimates bi-directional causal effects from observational data, even with invalid instruments, using a novel cluster fusion approach.

This paper provides identifiability guarantees for causal disentanglement from purely observational data using nonlinear additive Gaussian noise models, addressing a major challenge in causal represen…

Hybrid causal discovery algorithm efficiently learns unique causal graphs from observational data by leveraging local substructures and topological sorting, outperforming existing methods in accuracy …

Boosting, traditionally limited by assumptions about loss functions, is proven in this paper to efficiently optimize any loss function regardless of differentiability or convexity.

Higher-order PDEs hinder Physics-Informed Neural Network (PINN) convergence; this paper provides theoretical explanation and proposes variable splitting for improved accuracy.

Neural networks learn features effectively through gradient descent, not just at the beginning, but also at the end of training, even with carefully regularized objectives.

This study reveals how black-box settings affect the learning guarantee of stochastic compositional optimization, offering sharper generalization bounds and novel learning guarantees for derivative-fr…

Online fair division algorithm achieves Õ(T²/³) regret while guaranteeing envy-freeness or proportionality in expectation, a result proven tight.

Higher-Order Causal Message Passing (HO-CMP) accurately estimates treatment effects in complex systems with unknown interference by using observed data to learn the system’s dynamics over time.

First high-probability complexity guarantees for solving stochastic nonconvex minimax problems using a single-loop method are established.