phase transition

Cascade of phase transitions in the training of energy-based models NeurIPS 2024 Compression of Structured Data with Autoencoders: Provable Benefit of Nonlinearities and Depth ICML 2024 Deep Networks Always Grok and Here is Why ICML 2024 Generalization Bounds for Heavy-Tailed SDEs through the Fractional Fokker-Planck Equation ICML 2024 Grokking as a First Order Phase Transition in Two Layer Networks ICLR 2024 Grokking phase transitions in learning local rules with gradient descent JMLR 2024 How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective NeurIPS 2024 Low-degree phase transitions for detecting a planted clique in sublinear time COLT 2024 Risk-Sensitive Online Algorithms (Extended Abstract) COLT 2024 Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs ICLR 2024 Towards Theoretical Understandings of Self-Consuming Generative Models ICML 2024 Understanding the Expressivity and Trainability of Fourier Neural Operator: A Mean-Field Perspective NeurIPS 2024 A High-dimensional Convergence Theorem for U-statistics with Applications to Kernel-based Testing COLT 2023 Contextual Stochastic Block Model: Sharp Thresholds and Contiguity JMLR 2023 Near-optimal fitting of ellipsoids to random points COLT 2023 Phase transition for detecting a small community in a large network ICLR 2023 Phase Transitions in the Detection of Correlated Databases ICML 2023 Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer NeurIPS 2023 Sharp thresholds in inference of planted subgraphs COLT 2023 TP-Detector: Detecting Turning Points in the Engineering Process of Large-scale Projects EMNLP 2023 Uniqueness of BP fixed point for the Potts model and applications to community detection COLT 2023 Weak Recovery Threshold for the Hypergraph Stochastic Block Model COLT 2023 Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets ICML 2022 Asymptotics of smoothed Wasserstein distances in the small noise regime NeurIPS 2022 Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit NeurIPS 2022