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

207414621828 · Jun 202019922001200920172026
48 results for training paradigms

Combines cost-sensitive and Neyman-Pearson paradigms for better binary classification.

problem Asymmetric binary classification problems with unequal error severities.
method Develops TUBE-CS algorithm to bridge cost-sensitive and Neyman-Pearson paradigms.
result High-probability control of population type I error.

Adjoined Networks trains both base and compressed networks together for efficient model compression.

problem Efficiently compressing deep neural networks while maintaining accuracy.
method Adjoined Networks (AN) trains both a base network and a smaller compressed network simultaneously, sharing parameters.
result AN achieves 71.8% top-1 accuracy with 1.8M parameters and 1.6 GFLOPs on ImageNet.

Paper proposes SPO paradigm for better portfolio optimization in real markets.

problem Real-world trading frictions and constraints affect portfolio optimization quality.
method SPO paradigm with decision-focused training using surrogate loss and linear predictors.
result Decision-focused training improves risk-adjusted performance and robustness.

We explore the impact of learning paradigms on training deep neural networks for the Travelling Salesman Problem. We design controlled experiments to train supervised learning (SL) and reinforcement learning (RL) models on fixed graph sizes up to 100 nodes, and evaluate them on variable sized graphs up to 500 nodes. Be…

2019-10-16abs ↗pdf ↗

Survey on statistical theories of neural networks, focusing on approximation, training dynamics, and generative models.

problem Understanding the statistical properties and training dynamics of neural networks.
method Review of existing literature on neural networks from three perspectives: approximation, training dynamics, and generative models.
result Theoretical insights into neural network training dynamics and generative models.

Paper proposes verifier engineering for improving foundation models.

problem Challenges in providing effective supervision signals for foundation models.
method Leverages automated verifiers to perform verification tasks and deliver feedback.
result Verifier engineering can enhance foundation models' capabilities.

This review explores resampling techniques for imbalanced binary classification.

problem Imbalanced classes lead to poor prediction results in classification.
method Classical, cost-sensitive, and Neyman-Pearson paradigms with resampling techniques and classification methods.
result Complex dynamics among resampling techniques, base methods, metrics, and imbalance ratios.

New method improves language model fine-tuning without forgetting.

problem Fine-tuning language models to match specific distributions without forgetting.
method Combines Distribution Matching and Reinforcement Learning techniques.
result Adding a baseline improves constraint satisfaction, stability, and efficiency.

Crowdsourced training of large neural networks with decentralized Mixture-of-Experts.

problem Expensive training of large neural networks limits research contributions.
method Learning@home: decentralized Mixture-of-Experts for large, poorly connected participants.
result Performance and reliability of Learning@home surpass conventional distributed training.

Proposes a new stock prediction method that accounts for market dynamics.

problem The dynamic nature of the stock market invalidates traditional machine learning assumptions.
method Develops a second-order learning paradigm with multi-scale patterns.
result Demonstrates effectiveness in stock prediction on real-world data.

This paper establishes a theoretical foundation for super-models via domain adaptation.

problem Reducing computational and data costs in AI for small and medium-sized enterprises.
method Two-stage diffusion process modeling, including pre-training and fine-tuning stages, using the Uhlenbeck-Ornstein process.
result The generalization error of the fine-tuning stage is dominant in domain adaptation.

We introduce Invariant Risk Minimization (IRM), a learning paradigm to estimate invariant correlations across multiple training distributions. To achieve this goal, IRM learns a data representation such that the optimal classifier, on top of that data representation, matches for all training distributions. Through theo…

2019-07-05abs ↗pdf ↗

MapLUR uses deep learning on map images to estimate NO2 pollution, outperforming traditional methods.

problem Limited availability of data for traditional LUR models makes them hard to adapt to new areas.
method Data-driven, open-source approach using convolutional neural networks trained on map data.
result MapLUR significantly outperforms traditional LUR models, including those with manually engineered features.

This research formalizes inductive generalization and proposes a new learning paradigm called Inductive Learning.

problem Generalization from easy to hard tasks, especially out-of-domain generalization.
method Formalizes inductive generalization, introduces Inductive Learning, and outlines steps to adapt techniques for learning model successors.
result A new learning paradigm (Inductive Learning) that emphasizes induction and universal properties of learning and computation.

Novel RL-based NPG improves multi-objective NAS efficiency and performance.

problem Discovering optimal neural architectures with multiple conflicting objectives.
method Non-stationary policy gradient with adaptive reward functions and shared model.
result Framework efficiently approximates full Pareto front and achieves superior performance.

Paper proposes privacy-preserving learning for images, making them imperceptible to humans but recognizable by machines.

problem Conflict between developing AI systems and protecting sensitive training data.
method Encryption strategies (random shuffling and sub-patch mixing) followed by minimal adaptation to vision transformer.
result Achieves comparable accuracy to competitive methods while ensuring human-imperceptibility of encrypted images.

We propose a paradigm to deep-learn the ever-expanding databases which have emerged in mathematical physics and particle phenomenology, as diverse as the statistics of string vacua or combinatorial and algebraic geometry. As concrete examples, we establish multi-layer neural networks as both classifiers and predictors …

2017-06-08abs ↗pdf ↗

We consider the problem of training generative models with deep neural networks as generators, i.e. to map latent codes to data points. Whereas the dominant paradigm combines simple priors over codes with complex deterministic models, we propose instead to use more flexible code distributions. These distributions are e…

2017-07-28abs ↗pdf ↗

This paper improves model training by using a reference model to guide target model training.

problem Improving generalization and data efficiency in model training.
method DRRho risk minimization framework based on Distributionally Robust Optimization (DRO).
result DRRho risk minimization improves generalization and data efficiency compared to training without a reference model.

Theoretical justification for asymmetric actor-critic algorithms in reinforcement learning.

problem Lack of precise theoretical justification for asymmetric actor-critic algorithms in reinforcement learning.
method Adapting a finite-time convergence analysis to the asymmetric actor-critic setting with linear function approximators.
result A finite-time bound reveals that the asymmetric critic eliminates aliasing errors in the agent state.

ADAPT improves robustness of Vision Transformers without full model fine-tuning.

problem Vulnerability of Vision Transformers to adversarial attacks.
method Parameter-efficient prompt tuning with ADAPT framework for adaptive adversarial training.
result ADAPT achieves robust accuracy of ~40% w.r.t. SOTA methods using only ~1% of the parameters.

This paper bridges MTL and meta-learning, showing their shared structure and efficiency.

problem Improving generalization and adaptation in multi-task and few-shot learning.
method Theoretical analysis and empirical investigation of MTL and gradient-based meta-learning.
result MTL and GBML share similar optimization formulations and predictions over unseen tasks.

A framework for federated adversarial learning with convergence analysis.

problem Unique vulnerabilities to adversarial attacks in federated learning.
method Formulates a general federated adversarial learning framework with inner and outer loops for client-side adversarial training and server-side model aggregation.
result The minimum loss under the proposed algorithm can converge to ε with chosen learning rate and communication rounds.

Meta-CoTGAN improves adversarial text generation by preventing mode collapse.

problem Mode collapse in adversarial text generation.
method Meta-Cooperative Training Paradigm with a language model.
result Meta-CoTGAN effectively slows down mode collapse and improves generation quality and diversity.

Detects backdoors in outsourced models by replicating training steps across multiple servers.

problem Detecting backdoors in models trained on cloud providers without prior knowledge.
method Replicate training steps across multiple servers to identify deviations and malicious updates.
result 99.6% accuracy in identifying backdoored models out of 50% malicious providers.

Decodes neural activity to assess latent states in real-world driving tasks.

problem Understanding latent states during complex tasks in natural settings.
method Domain-generalized models trained on controlled lab paradigms applied to ecologically valid driving tasks.
result Changes in neural activity correlate with changes in behavior and task performance.

We present two paradigms relating algebraic, topological and quantum computational statistics for the topological model for quantum computation. In particular we suggest correspondences between the computational power of topological quantum computers, computational complexity of link invariants and images of braid grou…

2008-03-08abs ↗pdf ↗

Dynamic SBI improves SBI efficiency without rounds, reducing simulation and training costs.

problem Efficiently perform complex scientific inference with high-dimensional data.
method Adaptive dataset transformation, parallel simulation and training.
result Significant improvements in simulation and training efficiency.

In few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classification has featured meta-learning, in which a parameterized model for a learning algorithm is defined and trained on episodes representing different c…

2018-03-02abs ↗pdf ↗