Machine Learning

Novel generative models based on piecewise deterministic Markov processes (PDMPs) are introduced, offering efficient training procedures and theoretical guarantees, surpassing diffusion-based models i…

PHYSS-GP: a novel physics-informed state-space Gaussian process model for efficient spatio-temporal data modeling, outperforming existing methods in predictive accuracy and computational speed.

TREAT: a novel framework boosting dynamical systems modeling accuracy by enforcing Time-Reversal Symmetry (TRS) via a regularization term. High-precision modeling is achieved across diverse systems, …

Physically consistent multi-task learning bridges heterogeneous molecular data by directly leveraging physical laws to improve predictions, enhancing accuracy beyond the limitations of individual data…

TPGN, a novel framework for long-range time series forecasting, uses Parallel Gated Networks (PGN) to efficiently capture long-term dependencies, achieving state-of-the-art results on multiple dataset…

pFedClub: Controllable heterogeneous model aggregation boosts personalized federated learning by generating reasonable-sized, personalized models, significantly cutting computational costs.

Pessimistic Backward Policy for GFlowNets (PBP-GFN) tackles GFlowNets’ tendency to under-exploit high-reward objects by maximizing observed backward flow, enhancing high-reward object discovery and ov…

Fed-POE: A personalized federated learning algorithm for superior real-time predictions!

Personalized federated learning (PFL) often struggles with data scarcity and distribution shifts. pFedFDA, a novel algorithm, tackles this by framing representation learning as a generative modeling …

LM-WEATHER uses pre-trained language models to create highly accurate, personalized weather models directly on resource-constrained devices, achieving state-of-the-art results with significantly reduc…

Persistent Test-Time Adaptation (PeTTA) prevents AI model collapse in recurring scenarios by dynamically adjusting the adaptation strategy based on divergence from the initial model, ensuring long-ter…

Persistence Homology Distillation (PsHD) leverages topological data analysis to robustly preserve structural information in semi-supervised continual learning, significantly outperforming existing met…

PASQL, a novel periodic agent-state Q-learning algorithm, significantly improves reinforcement learning in partially observable environments by leveraging non-stationary periodic policies to overcome …

This paper proposes penalty-based methods for simple bilevel optimization, achieving (ε, εβ)-optimal solutions with improved complexity under Hölderian error bounds.

Colander: a novel auto-labeling technique boosts data efficiency by 60%, optimizing confidence functions for maximum coverage with minimal error.

PEAC: a novel unsupervised pre-training method significantly improves cross-embodiment generalization in reinforcement learning, enabling faster adaptation to diverse robots and tasks.

pcaGAN boosts posterior-sampling cGANs by using principal component regularization, achieving faster, more accurate results in various imaging tasks.

µPOCA: a new active learning approach maximizes model generalization using strategically acquired labels/features in data-scarce, costly scenarios with partial observability, leveraging LLMs for effic…

Boost continual reinforcement learning with Parseval regularization: maintaining orthogonal weight matrices preserves optimization, significantly improving RL agent training across diverse tasks.

PARD: a novel permutation-invariant autoregressive diffusion model for efficient and high-quality graph generation, achieving state-of-the-art results.