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

3677341,1001,467 · Jun 202019922001200920182026
48 results for search models

Deep-n-Cheap automates deep learning model search for low complexity.

problem Finding efficient deep learning models for various datasets.
method Automated search framework for architecture and hyperparameters, including search transfer.
result Models offer comparable performance to state-of-the-art but are faster to train.

MNMS learns from previous tasks to speed up model search for new tasks.

problem NAS requires extensive manual design and optimization for each new task.
method MNMS uses reinforcement learning to condition model construction on previously successful searches.
result MNMS can conduct simultaneous searches for multiple tasks and transfer knowledge to new tasks.

CrossBeam learns to search more efficiently in program synthesis.

problem Efficiently searching through vast program spaces.
method Trains a neural model to guide program synthesis, combining previously explored programs.
result CrossBeam explores much smaller portions of the program space compared to state-of-the-art methods.

FiGS searches over a larger space of architectures for efficient mobile models.

problem Designing small, efficient deep networks for mobile devices.
method Differentiable search method using sparse regularization and Logistic-Sigmoid distribution.
result FiGS produces state-of-the-art parameter-efficient models on ImageNet and improves object detection performance.

This paper compares Grid Search, Random Search, and Genetic Algorithm for NAS.

problem Hyperparameter optimization for neural architecture search.
method Comparison of Grid Search, Random Search, and Genetic Algorithm.
result Genetic Algorithm outperforms Grid Search and Random Search in terms of accuracy and execution time.

Bonsai-Net efficiently discovers state-of-the-art models with fewer parameters.

problem Efficiently discovering state-of-the-art neural architectures with minimal computational expense.
method Bonsai-Net uses a modified differential pruner to explore a relaxed search space.
result Bonsai-Net consistently discovers better architectures than random search with fewer parameters.

TGLS generates text by optimizing search results and learning from them.

problem Unsupervised text generation without explicit training data.
method TGLS uses simulated annealing to estimate sentence quality, then a conditional generative model learns from search results.
result TGLS outperforms unsupervised baselines and matches state-of-the-art supervised methods in paraphrase generation.

A new language for neural architecture search decouples search spaces and algorithms.

problem Current neural architecture search methods are limited to specific use-cases and lack general-purpose constructs.
method Proposes a formal language for encoding search spaces over general computational graphs, allowing modular, composable, and reusable encodings.
result The language enables easy experimentation with different search spaces and algorithms without reinventing the wheel.

Adaptive contrastive search improves text generation quality and diversity.

problem Decoding high-quality text from language model outputs.
method Adaptive contrastive search incorporating uncertainty-guided degeneration penalty.
result Enhanced text generation quality and diversity across different models and datasets.

Efficient search methods can outperform random search on challenging tasks.

problem Comparing the performance of efficient and random search methods in neural architecture search.
method Comparison of weight sharing and random search methods on progressively larger search spaces for image classification and detection.
result Efficient search methods can provide substantial gains over random search on large, realistic tasks.

Efficient neural architecture search by sampling structure and operations.

problem Efficiently searching for optimal neural architectures.
method Decouples structure and operation search, using reinforcement learning with policy vectors.
result Significantly improved efficiency compared to traditional methods.

Paper tackles NAS problem by modeling it as a sparse supernet.

problem Neural Architecture Search (NAS) problem, particularly Mixed-Path Search.
method Model NAS as a sparse supernet with sparsity constraints. Use hierarchical accelerated proximal gradient algorithm for optimization.
result Proposed method finds compact, general, and powerful neural architectures.

LA-MCTS learns search space partition for black-box optimization using Monte Carlo Tree Search.

problem High-dimensional black-box optimization challenges.
method LA-MCTS recursively splits search space into regions with high/low function values, learns nonlinear partition and local models online.
result LA-MCTS achieves strong performance in black-box optimization and reinforcement learning benchmarks, especially for high-dimensional problems.

A method for policy search with high-dimensional context variables.

problem Learning from high-dimensional context variables like camera images is challenging.
method Model-based relative entropy stochastic search framework with integrated dimensionality reduction.
result The proposed method outperforms naive dimensionality reduction methods.

New algorithms improve contextual search in the presence of adversarial corruptions.

problem Improving search accuracy in dynamic pricing settings with corrupted responses.
method Two algorithms based on binary search and gradient descent methods.
result Achieve near-optimal regret in the absence of adversarial corruptions and gracefully degrade with corrupted agents.

This work recommends personalized search stories to users based on their interests.

problem Personalized search story recommendation within search engines.
method Deep reinforcement learning architecture trained by imitation learning and reinforcement learning.
result Empirically demonstrated effectiveness on real-world data sets.

Paper tackles real-world e-commerce search efficiency and user experience.

problem Efficiently rank large-scale e-commerce search results with multiple factors.
method Design and deploy a novel Cascade ranking model in a large-scale operational e-commerce search application.
result Demonstrates the advantage of the proposed model in addressing multiple factors of effectiveness, efficiency, and user experience.

SAVE combines Q-learning and MCTS with amortized value estimates for improved performance.

problem Combining model-free Q-learning and model-based MCTS for efficient learning and planning.
method SAVE uses a learned prior to guide MCTS, which estimates improved state-action values. These estimates are used to update the prior, creating a cooperative relationship between learning and search.
result SAVE achieves higher rewards with fewer training steps and strong performance with small search budgets.

A new search-control strategy improves Dyna's efficiency.

problem Improving sample efficiency in model-based reinforcement learning.
method Proposes a novel search-control strategy by sampling high frequency regions of the value function.
result Empirically shows that high frequency regions require more samples to approximate, suggesting a better search-control strategy.

Study compares variable selection methods for model evaluation and search.

problem Understanding underlying mechanisms in scientific questions through variable selection.
method Comprehensive comparison of BIC and AIC for model evaluation and various search methods (exhaustive, greedy, LASSO path, stochastic search) for model space exploration.
result Exhaustive search BIC and stochastic search BIC outperform other methods in small and large model spaces, respectively, improving correct identification rate and reducing false discovery rate.

Framework for automatically designing and training deep models.

problem Manual design of deep architectures is slow and error-prone.
method Extensible language for representing complex search spaces over architectures and hyperparameters. Uses tree-structured search spaces and various algorithms like MCTS and SMBO.
result MCTS and SMBO outperform random search in model training.

Efficient algorithm finds fast Transformer models.

problem Slow inference time of Transformer models.
method Decompose Transformer architecture into components, use sampling-based one-shot search.
result Achieved 10% to 30% speedup on pre-trained BERT and 70% on top of a previous state-of-the-art model.

Predict accuracy of neural architectures using non-neural models.

problem Improving efficiency and effectiveness of neural architecture search.
method Used gradient boosting decision tree (GBDT) for accuracy prediction and pruned the search space based on features learned from GBDT.
result GBDT-based predictor achieves comparable or better accuracy than neural network-based predictors and is 22x more sample efficient on NASBench-101.

Method predicts disease outbreaks using search logs, overcoming instability.

problem Predicting disease outbreaks from search logs is challenging due to short-term and long-term instability.
method Seasonal-adjustment method decomposes logs into seasonal, trend, and irregular components; feature selection method selects relevant search terms.
result Proposed method outperforms comparative methods in prediction accuracy for seven of ten diseases.

HotNAS reduces AI search time from hundreds of GPU hours to less than 3 GPU hours.

problem High time required for AI solution generation from scratch.
method HotNAS starts from a 'hot' state using pre-trained models and integrates compression during co-search.
result Reduces search time from 200 GPU hours to less than 3 GPU hours.

Graph-based NAS improves sample efficiency in architecture design.

problem Current NAS search spaces are static sequences, limiting expressiveness.
method Proposed graph-based search space with vertices and edges for iterative and branching decisions.
result Graph representation improves sample efficiency in architecture design.

AutoOD automates outlier detection using curiosity-guided search and self-imitation learning.

problem Automated outlier detection for complex tasks with big data.
method Curiosity-guided search strategy and self-imitation learning.
result AutoOD identifies optimal neural network models with superior performance.

This study investigates global normalization in neural models, showing its effectiveness in search-aware training.

problem Theoretical equivalence of global and local normalization in high-capacity models, practical advantage unclear.
method Continuous relaxation of beam search for training globally normalized recurrent sequence models.
result Globally normalized models are more effective than locally normalized ones in inexact search.

This research explores various sampling methods and probability distributions for hard alignment in sequence-to-sequence TTS synthesis.

problem Improving alignment accuracy in sequence-to-sequence text-to-speech synthesis.
method Investigated various sampling methods (greedy, beam, random) and probability distributions (Bernoulli, Concrete) for hard alignment.
result Deterministic search is more preferable than stochastic search for natural alignment transition.