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.

168,742 papers · 148 categories

Trend · papers per month

210421631841 · Jun 202019922001200920172026
48 results for early training stages

Enhances early risk assessments for pediatric outcomes using contrastive learning.

problem Improving risk assessments in early stages of pediatric development.
method Contrastive multi-modal framework that treats each time window as a distinct modality, training on all available data.
result Consistent improvements in early-stage risk assessments validated on real-world tasks.

A new method reduces variance in training early-stage rankers for large-scale search systems.

problem Training early-stage rankers for large-scale search systems is challenging due to exploding variance in policy gradient methods.
method Proposes credit-assigned policy gradient (CA-PG) to mitigate variance in training early-stage rankers.
result CA-PG significantly reduces variance in training early-stage rankers compared to vanilla policy gradient.

Improves classifier performance in multi-stage selection processes.

problem Difficulty in training classifiers in multi-stage selection processes due to varying sample sizes and information.
method Multi-Stage Transfer Learning (MSGTL) approach that uses knowledge from simpler classifiers trained in early stages to improve later stages.
result MSGTL outperforms other transfer learning methods in real-world selection process data.

Gradient descent learns useful features even in the NTK regime.

problem The ability of neural networks to learn useful features.
method Local convergence analysis of gradient descent with regularization.
result Gradient descent can capture ground-truth directions for feature learning even after the loss threshold is reached.

Improves classifier performance in multi-stage processes with adversarial autoencoders and multi-task learning.

problem Challenges in training classifiers due to varying sample sizes and information content across stages.
method Combines adversarial autoencoders, multi-task learning, and semi-supervised learning to address underfitting and overfitting.
result Our approach outperforms state-of-the-art methods across different domains.

Dynamic Influence Tracker measures changing sample importance during model training.

problem Static influence measurements during training overlook how sample importance varies over time.
method Dynamic Influence Tracker (DIT) captures time-varying sample influence across arbitrary time windows.
result DIT reveals distinct learning phases with shifting priorities and detects corrupted samples more efficiently.

ABS dynamically adjusts batch size based on policy stability, improving RL performance.

problem Diminishing returns with large batch sizes in RL due to non-stationary data.
method Adaptive Batch Scaling (ABS) with Behavioral Divergence metric.
result Larger batch sizes can improve RL performance, contrary to conventional wisdom.

Early training of deep neural networks leads to small, directionally converging weights.

problem Training dynamics of deep homogeneous neural networks with small initializations.
method Gradient flow analysis and study of KKT points for neural correlation function.
result Weights converge in direction to KKT points during early training stages.

We estimate treatment cost-savings from early cancer diagnosis. For breast, lung, prostate and colorectal cancers and melanoma, which account for more than 50% of new incidences projected in 2017, we combine published cancer treatment cost estimates by stage with incidence rates by stage at diagnosis. We extrapolate to…

2017-08-30abs ↗pdf ↗

Early alignment in neural networks leads to sparse representations but hinders convergence.

problem The implicit bias of gradient descent during early training phases.
method Quantitative description of early alignment phase in small initialisation, one hidden layer networks.
result Early alignment induces a sparse representation but also hinders convergence to global minima.

Neural networks learn clean data patterns first, then noisy data, leading to improved performance initially but deteriorating later.

problem Improvement in prediction error on clean data during early training of neural networks with noisy labels.
method Theoretical analysis and experiments to explore the dynamics of gradient descent and the impact of clean and noisy data.
result Neural networks prioritize learning clean data patterns first, leading to improved performance initially but deteriorating later due to diminishing gradient dominance of clean samples over noisy ones.

Enhances diffusion models by preprocessing data to improve reconstruction quality.

problem Slow sampling and poor reconstruction quality in diffusion models, especially for small-scale networks.
method Applying Gaussianization preprocessing to the training data to make the target distribution more Gaussian-like.
result Improves generation quality, especially in the early stages of reconstruction with small networks.

Hierarchical neural networks are exponentially more efficient than their corresponding "shallow" counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. By approximating the tangent subspace, we suggest a sparse representation that enables switching to …

2019-12-18abs ↗pdf ↗

Machine learning detects subtle glucose changes for early diabetes diagnosis.

problem Challenging early-stage diabetes diagnosis due to subtle glucose changes.
method Applied machine learning to synthetic glucose profiles generated by a biophysical model.
result High accuracy (above 85%) in detecting insulin resistance using various neural networks.

The paper introduces a novel method for training neural network Stein critics with staged L2L^2-regularization.

problem Learning to differentiate model distributions from observed data in high-dimensional settings.
method Developed a novel staging procedure for L2L^2 regularization over training time, leveraging the advantages of highly-regularized training at early times.
result Theoretical guarantees and empirical validation show that the method improves the approximation of the training dynamic by the kernel optimization, leading to faster convergence and better performance.

Study evaluates early-stage cybersecurity firms' performance using Crunchbase data.

problem Assessing performance of early-stage cybersecurity startups.
method Empirical analysis of 19 cybersecurity sectors using Crunchbase data.
result Significant variations in capital raised and post-money valuations across cybersecurity sectors.

It is typical for a machine learning system to have numerous hyperparameters that affect its learning rate and prediction quality. Finding a good combination of the hyperparameters is, however, a challenging job. This is mainly because evaluation of each combination is extremely expensive computationally; indeed, train…

2019-07-19abs ↗pdf ↗

Paper introduces DTAE to optimize RL algorithms, balancing exploration and exploitation.

problem Balancing exploration and exploitation in reinforcement learning.
method Soft policy optimization with entropy and dual-track advantage estimator (DTAE).
result DTAE accelerates RL algorithm convergence and improves performance.

Meta-learning is a promising method to achieve efficient training method towards deep neural net and has been attracting increases interests in recent years. But most of the current methods are still not capable to train complex neuron net model with long-time training process. In this paper, a novel second-order meta-…

2018-05-22abs ↗pdf ↗

The paper analyzes CFG in masked diffusion models and proposes a new method to improve sample quality.

problem Improving sample quality in conditional generation with CFG in masked diffusion models.
method Analyzing CFG's effect in a low-dimensional masked diffusion model, revealing early-stage guidance harms quality and late-stage improves it. Proposed a novel method to smooth transitions between distributions.
result The proposed method improves sample quality via a simple one-line code change.

The study analyzes how label noise affects deep learning feature learning.

problem The impact of label noise on deep learning feature learning.
method Theoretical analysis of a two-layer convolutional neural network under noisy label conditions.
result Two key stages identified: signal learning in Stage I and noise memorization in Stage II.

New insights into how to inspect and learn from multi-stage processes and AI reasoning.

problem Understanding how to attribute outcomes to early stages in multi-stage operations and AI reasoning.
method Information-theoretic analysis and mathematical proofs of four key results.
result Uniform checkpoint spacing is minimax-optimal for inspection design under homogeneous signal attenuation.

Two-layer networks favor simple features, especially in complex datasets.

problem Simplicity bias in neural networks over-reliing on simple features.
method Characterization of two-layer neural networks with small weights and gradient flow.
result Features learned in middle training stages are more useful for out-of-distribution transfer.

Gradient descent reshapes the function space of neural networks.

problem Understanding how feature learning affects the function space of neural networks.
method Characterized the evolution of the feature space during training using a two-layer neural network.
result Gradient descent induces a data-adaptive deformation that selectively enhances signal-aligned directions.

Two-layer ReLU networks often converge to simpler solutions, improving generalization.

problem Understanding generalization in overparametrized neural networks, especially for complex tasks.
method Theoretical analysis of two-layer ReLU networks, focusing on the early alignment phase.
result Two-layer ReLU networks often converge to simpler solutions rather than interpolating the training data, leading to better generalization.

A game-theoretic framework identifies influential hyperparameters for neural networks.

problem Understanding which hyperparameters are most important for neural network performance.
method Employing Shapley Effects for global sensitivity analysis and Pareto front sets for identifying effective configurations.
result Reveals which hyperparameters are most influential for different objectives in neural networks.

A new multi-view clustering method that is fast, scalable, and easy to use.

problem High computational complexity, one-stage fusion, and dataset-specific hyperparameter tuning in multi-view clustering.
method Random view groups, hybrid early-late fusion, diversified base clusterings, and unified bipartite graph.
result Almost linear time and space complexity, no dataset-specific tuning required.

This paper simplifies fine-tuning for small LLMs, reducing barriers for developers.

problem Limited resources for fine-tuning large language models (LLMs) by individual developers and small organizations.
method Instruction-tuning datasets, small-sized LLMs (3B to 7B parameters), various training configurations and strategies.
result Improved model performance on benchmarks with specific training configurations, and insights into early termination and hyperparameter simplifications.

Enhances early-exit neural networks for anytime classification.

problem Lack of guaranteed prediction quality improvement with longer computation time.
method Post-hoc modification based on Product-of-Experts to enforce conditional monotonicity.
result Achieves conditional monotonicity in prediction quality, enabling anytime classification.

The difficulty of classification affects the weight matrices' heavy tail appearance in deep learning networks.

problem Understanding the spectral properties of weight matrices in deep learning networks.
method Spectral analysis of weight matrices in different modules of DNNs, classification difficulty as a driving factor for heavy tail appearance.
result Higher classification difficulty leads to more frequent appearance of heavy tails in weight matrices spectra.