arXiv research

Graph networks struggle with multi-task learning due to varying property loss surface curvatures.

The staircase property aids deep learning by guiding hierarchical feature learning.

Improved molecular property prediction using multitask learning.

Machine learning predicts liquid water properties from cluster data.

Unified framework supports lifelong learning properties.

Deep models generate geometric objects with global properties.

ASGN uses active semi-supervised learning to predict molecular properties efficiently.

Paper verifies RNNs using automata learning and model checking.

Deep learning speeds up material property quantification using stress waves.

Hybrid model speeds up galaxy simulations by incorporating baryonic properties.

Flexible Kernels for Protein Property Prediction

Study generalizes property elicitation to imprecise probabilities.

Study builds ML models to predict fuel properties accurately.

New method improves submodular maximization for machine learning applications.

Framework for interpreting ML models to reveal properties of real-world phenomena.

Generative model learns to create molecules with multiple properties using interpretable substructures.

Model predicts price polarity of real estate properties using website information.

This paper explores how environmental properties can simplify reinforcement learning in non-episodic settings.

The article proposes a deep learning method to test and infer the Markov property in time series data.

FlowMO uses Gaussian Processes for molecular property prediction with uncertainty.

Study shows dataset properties impact adversarial machine learning robustness.

Two ML frameworks predict antibody properties using structural data.

We propose a framework for the completely unsupervised learning of latent object properties from their interactions: the perception-prediction network (PPN). Consisting of a perception module that extracts representations of latent object properties and a prediction module that uses those extracted properties to simula…

Multi-party machine learning leaks global dataset properties even with black-box access.

Large learning rates enhance model robustness and compressibility.

New method uses cycle consistency to enforce invariance in latent space.

We study the generalization properties of ridge regression with random features in the statistical learning framework. We show for the first time that $O(1/\sqrt{n})$ learning bounds can be achieved with only $O(\sqrt{n}\log n)$ random features rather than $O({n})$ as suggested by previous results. Further, we prove fa…

New approach identifies latent properties from mechanisms, not just data.

MCML uses ML to study learnability of Alloy properties, showing simple models can perform well but fail on full input space.

Paper explores RKHS properties for derivative and integral operators.

We propose a novel computational strategy for de novo design of molecules with desired properties termed ReLeaSE (Reinforcement Learning for Structural Evolution). Based on deep and reinforcement learning approaches, ReLeaSE integrates two deep neural networks - generative and predictive - that are trained separately b…

Lectures on deep learning properties in infinite and large-width networks.

Paper tackles robust prediction of nuclear reactor materials under scarce data.

Meta-learning symbolic default hyperparameters from dataset properties.

Machine learning identifies string models with correct gauge groups and chiral asymmetry.

Persistent homology enhances graph classification by capturing long-range graph properties.

Develops a learning algorithm for PSL formulas from examples.

New graph properties inherited by Frechet mean and median.

Deep learning model improves seismic rock property estimation.

Pricing a rental property on Airbnb is a challenging task for the owner as it determines the number of customers for the place. On the other hand, customers have to evaluate an offered price with minimal knowledge of an optimal value for the property. This paper aims to develop a reliable price prediction model using m…

Paper tackles multi-task learning for molecular property prediction with limited data.

New analysis shows LLMs don't follow Bayesian inference in ICL.

The paper extends sequences while preserving statistical properties using a mixture model.

The versatility of exponential families, along with their attendant convexity properties, make them a popular and effective statistical model. A central issue is learning these models in high-dimensions, such as when there is some sparsity pattern of the optimal parameter. This work characterizes a certain strong conve…

This study compares transfer learning and self-supervised learning for better model performance.

Develops Active Fourier Auditor to estimate ML model properties without reconstructing them.

We present a framework that enables estimation of low-dimensional sub-resolution reservoir properties directly from seismic data, without requiring the solution of a high dimensional seismic inverse problem. Our workflow is based on the Bayesian evidential learning approach and exploits learning the direct relation bet…

We introduce a new algorithm, called CDER, for supervised machine learning that merges the multi-scale geometric properties of Cover Trees with the information-theoretic properties of entropy. CDER applies to a training set of labeled pointclouds embedded in a common Euclidean space. If typical pointclouds correspondin…