Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

4198381,2571,676 · Jun 202019922001200920172026
48 results for Learning Properties

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

problem Graph networks underperform in multi-task learning for crystal and molecule properties.
method Assessed curvature of property loss surfaces via spectral properties of Hessians, matrix-free using randomized numerical linear algebra.
result Varying curvature of property loss surfaces explains graph networks' multi-task learning inefficiency.

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

problem Understanding how hierarchical structure influences deep learning performance.
method Defined and proved the staircase property for Boolean hypercube functions, and showed its learnability by layerwise stochastic coordinate descent.
result Staircase functions can be learned in polynomial time using layerwise stochastic coordinate descent on regular neural networks.

Machine learning predicts liquid water properties from cluster data.

problem Accuracy of bulk properties from machine-learned potentials is limited by training data.
method Local, atom-centred descriptors enable prediction of bulk properties from cluster data.
result Excellent agreement with experimental and theoretical counterparts of liquid water properties.

Deep models generate geometric objects with global properties.

problem Comparing neural models' global properties from generated samples.
method Training on datasets of reflexive polytopes, comparing different representations.
result Models learn non-trivial global properties of geometric objects.

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

problem Predicting molecular properties with scarce labeled data and high computational cost.
method ASGN combines a teacher-student framework with active learning to handle joint representation and property learning.
result ASGN achieves remarkable performance in property prediction on public datasets.

Hybrid model speeds up galaxy simulations by incorporating baryonic properties.

problem Inaccurate baryonic properties in dark matter-only simulations.
method Combining analytic models and machine learning for faster, more accurate simulations.
result Hybrid model outperforms machine learning alone for some baryonic properties.

Study builds ML models to predict fuel properties accurately.

problem Accurate prediction of liquid fuel properties over a wide range of conditions.
method Used Gaussian Processes and probabilistic conditional generative learning to train ML models on fuel density data.
result ML models can predict fuel properties accurately across various pressure and temperature conditions.

New method improves submodular maximization for machine learning applications.

problem Inexact monotonicity in submodular functions limits traditional algorithms' performance.
method Introduces monotonicity ratio as a continuous version of monotonicity, leading to improved approximation guarantees.
result Improved approximation ratios for movie recommendation, quadratic programming, and image summarization.

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

problem Lack of direct interpretability in modern ML models hinders scientific understanding.
method Developed 'property descriptors' grounded in statistical learning theory.
result Property descriptors can reveal relevant properties of joint probability distributions.

Humans can learn a variety of concepts and skills incrementally over the course of their lives while exhibiting many desirable properties, such as continual learning without forgetting, forward transfer and backward transfer of knowledge, and learning a new concept or task with only a few examples. Several lines of mac…

2019-11-21abs ↗pdf ↗

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

problem Challenges in reinforcement learning with continuous interaction and sparse delayed rewards.
method Analysis of environment shaping and dynamism properties to simplify learning.
result Properties like environment shaping and dynamism can significantly ease learning in non-episodic, sparse reward settings.

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

problem Testing and inferring the Markov property in high-dimensional time series data.
method Deep conditional generative learning to estimate conditional density functions and derive a doubly robust test statistic.
result The test controls the type-I error asymptotically and has power approaching one.

FlowMO uses Gaussian Processes for molecular property prediction with uncertainty.

problem Predicting molecular properties with uncertainty for small datasets.
method Gaussian Processes implemented in FlowMO, built on GPflow and RDKit.
result Comparable predictive performance to deep learning but superior uncertainty calibration.

Two ML frameworks predict antibody properties using structural data.

problem Predicting antibody properties using sequence and structural data.
method ANTIPASTI and INFUSSE models using graph representations and neural networks.
result ANTIPASTI predicts binding affinity; INFUSSE predicts residue flexibility.

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

problem Leakage of global dataset properties in multi-party machine learning.
method Demonstrated leakage of sensitive attribute distributions in pooled data.
result A curious party can infer sensitive attribute distributions in other parties' data with high accuracy.

Large learning rates enhance model robustness and compressibility.

problem Achieving robustness and resource-efficiency in machine learning models.
method Identifying and utilizing large learning rates as a facilitator for robustness and compressibility.
result Large learning rates produce desirable representation properties and compare favorably to other methods.

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

problem Learning meaningful and independent factors of variation in datasets.
method Two separate latent subspaces, cycle consistency constraints, deep information bottleneck.
result Identifies more meaningful factors leading to sparser and interpretable models.

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/n)O(1/\sqrt{n}) learning bounds can be achieved with only O(nlogn)O(\sqrt{n}\log n) random features rather than O(n)O({n}) as suggested by previous results. Further, we prove fa…

2016-02-14abs ↗pdf ↗

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

problem Identifying latent properties from data generating processes.
method Equivariance perspective on identifiable representation learning.
result Identification of latent properties is possible up to shared equivariances in known mechanisms.

Paper explores RKHS properties for derivative and integral operators.

problem Establishing sufficient conditions for reproducing property in RKHS.
method Establishing reproducing property for combinations of composition operators.
result Provides framework for regularized learning algorithms involving function values, gradients, or 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…

2017-11-29abs ↗pdf ↗

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

problem Understanding deep neural networks in extreme width conditions.
method Analysis of random deep neural networks, connections to linear models, kernels, and Gaussian processes, perturbative and non-perturbative treatments.
result Properties and behaviors of deep neural networks in the infinite-width limit and large-width regime.

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

problem Challenges of data scarcity and uncertainty in nuclear reactor design.
method Meta-learning approach informed by uncertainty and prior knowledge.
result Achieves superior performance in rupture life prediction.

Meta-learning symbolic default hyperparameters from dataset properties.

problem Empirical hyperparameter optimization is slow and requires manual configuration.
method Evolutionary algorithm to learn symbolic hyperparameter formulas from dataset properties.
result Meta-learning finds viable symbolic defaults for ML algorithms.

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

problem Lack of formal assessment of persistent homology in graph learning.
method Brief introduction and theoretical discussion of persistent homology in graph context, followed by empirical analysis.
result Persistent homology improves graph classification, especially for data with prominent topological structures.

Deep learning model improves seismic rock property estimation.

problem Estimating reservoir rock properties from seismic reflection data.
method Proposes a deep learning-based seismic inversion workflow that models seismic traces spatiotemporally.
result Achieves best performance on SEAM dataset with r2r^{2} coefficient of 79.77\%

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…

2019-07-29abs ↗pdf ↗

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

problem Limited labeled data for each molecular property task in drug discovery.
method Proposes SGNN-EBM method to utilize relation graph between tasks and improve multi-task learning performance.
result Empirical results show the effectiveness of SGNN-EBM.

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

problem Does in-context learning in LLMs follow Bayesian inference?
method Analyzes ICL through the martingale property, a requirement for Bayesian inference.
result Violations of the martingale property show LLMs don't follow Bayesian inference.

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

problem Extending sequences while retaining their statistical properties.
method Auto-regressive Sequence Extension Mixture Model (SEMM) using deep learning.
result The mixture model outperforms traditional neural networks in sequence extension with statistical property retention.

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

problem Choosing between transfer learning and self-supervised learning for optimal model performance.
method Comprehensive comparative study of transfer learning and self-supervised learning under various data and task properties.
result Self-supervised learning outperforms transfer learning in certain applications, and vice versa.

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

problem Verifying and auditing properties of Machine Learning models in real-world applications.
method A new framework that quantifies ML model properties using Fourier coefficients, without reconstructing the model.
result Active Fourier Auditor (AFA) is more accurate and sample-efficient than baselines for estimating robustness, individual fairness, and group fairness.

ExpCLR uses expert features to improve time-series representation learning.

problem Current representation learning approaches fail to ensure useful properties for time-series data.
method ExpCLR employs expert features to replace data transformations in contrastive learning, ensuring two useful properties for time-series representations.
result ExpCLR outperforms state-of-the-art methods on three real-world time-series datasets.