↓Skip to main content

Machine Learning

A probability contrastive learning framework for 3D molecular representation learning
·2012 words·10 mins· loading · loading
Machine Learning Self-Supervised Learning 🏢 University at Buffalo
A novel probability-based contrastive learning framework significantly improves 3D molecular representation learning by mitigating false pairs, achieving state-of-the-art results.
A PID Controller Approach for Adaptive Probability-dependent Gradient Decay in Model Calibration
·2215 words·11 mins· loading · loading
Machine Learning Deep Learning 🏢 Jiangnan University
Deep learning models often suffer from overconfidence; this paper introduces a PID controller to adaptively adjust a probability-dependent gradient decay rate, ensuring consistent optimization of both…
A New Neural Kernel Regime: The Inductive Bias of Multi-Task Learning
·4930 words·24 mins· loading · loading
AI Generated Machine Learning Deep Learning 🏢 University of Wisconsin-Madison
Multi-task learning with shallow ReLU networks yields almost always unique solutions equivalent to kernel methods, unlike single-task settings.
A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
·317 words·2 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 UC Los Angeles
MQL-UCB: Near-optimal reinforcement learning with low policy switching cost, solving the exploration-exploitation dilemma for complex models.
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
·1860 words·9 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 University of Alberta
New empirical methodology quantifies how much reinforcement learning algorithm performance relies on per-environment hyperparameter tuning, enabling better algorithm design.
A Metalearned Neural Circuit for Nonparametric Bayesian Inference
·2042 words·10 mins· loading · loading
Machine Learning Meta Learning 🏢 Princeton University
Metalearning a neural circuit mimics nonparametric Bayesian inference, enabling fast, accurate, open-set classification.
A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks
·2008 words·10 mins· loading · loading
Machine Learning Deep Learning 🏢 Ant Group
LNGD: A Layer-Wise Natural Gradient optimizer drastically cuts deep neural network training time without sacrificing accuracy.
A Kernel Perspective on Distillation-based Collaborative Learning
·2168 words·11 mins· loading · loading
Machine Learning Federated Learning 🏢 Korea Advanced Institute of Science and Technology
This paper introduces DCL-KR and DCL-NN, novel distillation-based collaborative learning algorithms achieving nearly minimax optimal convergence rates in heterogeneous environments without direct data…
A Generative Model of Symmetry Transformations
·3610 words·17 mins· loading · loading
Machine Learning Generative Learning 🏢 University of Cambridge
Generative model learns data symmetries for improved efficiency and higher test log-likelihoods.
A Functional Extension of Semi-Structured Networks
·2279 words·11 mins· loading · loading
Machine Learning Deep Learning 🏢 Munich Center for Machine Learning (MCML)
This paper introduces semi-structured functional networks (SSFNNs), a novel approach that combines interpretable functional regression models with deep neural networks, achieving both high accuracy an…
A Framework for Bilevel Optimization on Riemannian Manifolds
·1520 words·8 mins· loading · loading
Machine Learning Meta Learning 🏢 RIKEN AIP
This paper introduces a novel framework for bilevel optimization on Riemannian manifolds, providing efficient hypergradient estimation strategies and convergence analysis, with successful applications…
A Foundation Model for Zero-shot Logical Query Reasoning
·2687 words·13 mins· loading · loading
Machine Learning Deep Learning 🏢 Intel AI Lab
ULTRAQUERY: a groundbreaking foundation model for zero-shot logical query reasoning on any knowledge graph, surpassing existing methods’ limitations.
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
·3886 words·19 mins· loading · loading
AI Generated Machine Learning Deep Learning 🏢 Technion - Israel Institute of Technology
Flexible Subgraph GNNs, achieving scalability via graph products and coarsening, consistently outperform baselines and adapt to varying subgraph numbers.
A Canonicalization Perspective on Invariant and Equivariant Learning
·2927 words·14 mins· loading · loading
AI Generated Machine Learning Deep Learning 🏢 Peking University
Canonicalization simplifies invariant and equivariant learning by connecting frames to canonical forms, leading to novel, superior frame designs for eigenvector symmetries.
A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
·484 words·3 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 Churney ApS
New best-of-both-worlds bandit algorithm tolerates arbitrary excessive delays, overcoming limitations of prior work that required prior knowledge of maximal delay and suffered linear regret dependence…
A Bayesian Approach to Data Point Selection
·3079 words·15 mins· loading · loading
AI Generated Machine Learning Deep Learning 🏢 Microsoft Research
BADS: a novel Bayesian approach to data point selection efficiently optimizes deep learning models by jointly inferring instance weights and model parameters using stochastic gradient Langevin dynamic…
A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings
·1730 words·9 mins· loading · loading
Machine Learning Federated Learning 🏢 University of Texas at Austin
FedBNN: a novel Bayesian framework for personalized federated learning, achieves superior performance in heterogeneous settings while ensuring strict privacy via differential privacy.
4-bit Shampoo for Memory-Efficient Network Training
·3782 words·18 mins· loading · loading
AI Generated Machine Learning Deep Learning 🏢 Beijing Normal University
4-bit Shampoo achieves comparable performance to its 32-bit counterpart while drastically reducing memory usage, enabling efficient training of significantly larger neural networks.
$psilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
·1776 words·9 mins· loading · loading
Machine Learning Deep Learning 🏢 Faculty of Computing, Harbin Institute of Technology
e-Softmax: A simple plug-and-play module enhances deep learning model robustness against noisy labels by approximating one-hot vectors, achieving noise-tolerant learning with controllable excess risk.
$C^2M^3$: Cycle-Consistent Multi-Model Merging
·3768 words·18 mins· loading · loading
Machine Learning Federated Learning 🏢 Sapienza University of Rome
C2M³: A novel data-free method ensures cycle-consistent merging of neural networks, significantly improving model aggregation across various architectures and datasets.