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.

169,341 papers · 148 categories

Trend · papers per month

1122 · Feb 202019922001200920182026
13 results for reinitialization

Selective reinitialization improves adaptability of neural bandits in dynamic environments.

problem Loss of plasticity in neural bandits, leading to rigid neural network parameters.
method Selective Reinitialization (SeRe) framework that dynamically resets underutilized units.
result SeRe enhances adaptability of CNB algorithms, reducing cumulative regret in dynamic environments.

Study examines effects of pruning techniques on deep learning models.

problem Understanding the impact of pruning methods on deep learning model structure and dynamics.
method Investigated differences in connectivity and learning dynamics of pruned models using various iterative pruning techniques.
result Emergence of structure in pruned models through magnitude-based unstructured pruning and weight rewinding.

Enhanced quantum synchronization achieved using quantum machine learning.

problem Quantum synchronization between two systems with different loss/decoherence mechanisms.
method Digital-analog decomposition of the master equation, quantum machine learning protocol with projective measurements and reinitialization.
result Quantum machine learning protocol enhances synchronization even with different loss/decoherence mechanisms.

New insights into why sparse networks perform well, including Supermasks.

problem Understanding why sparse networks trained from scratch perform better than non-sparse models.
method Analyzed three critical components of the Lottery Ticket algorithm: zeroing weights, signs, and masking.
result Discovered Supermasks that can improve performance of untrained networks.

Early neural network training reveals important sub-networks and weight distributions.

problem Understanding the early phases of neural network training.
method Extensive measurements and quantitative probing of weight distribution and dataset reliance.
result Deep networks are not robust to reinitializing with random weights while maintaining signs, and weight distributions are highly non-independent.

Extends a model for limit order markets to more flexible distributions.

problem Modeling the dynamics of limit order markets with flexible distributions.
method Uses Markov renewal processes to model bid and ask queues, keeping analytical tractability.
result Calibrated model accurately represents market data for five stocks.

A real-time federated neural architecture search approach reduces costs and improves performance.

problem High communication and computational demands in federated learning for large models.
method Evolutionary approach with double-sampling technique to optimize model performance and reduce costs.
result Effective real-time federated neural architecture search for deep models on edge devices.

RIFLE improves deep transfer learning by reinitializing fully-connected layers.

problem Limited improvement in transfer learning accuracy with pre-trained models on small datasets.
method Re-Initializing fully-connected layers with random scratch during fine-tuning.
result Significant improvement in deep transfer learning accuracy across various datasets.

Deep learning predicts curvature of 2D interfaces in level-set method.

problem Estimating curvature in level-set method for complex interfaces.
method Deep learning using feed-forward neural networks trained on synthetic data.
result Deep learning models approximate curvature with comparable precision to traditional methods.

Paper introduces a simulator-free approach to reinforcement learning policy distillation.

problem Learning multiplicity of cases corresponding to a given action in reinforcement learning.
method Generative adversarial approach to find multiple exemplars for each output class.
result Improves over state-of-the-art on data-free learning of student networks.