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.

169,291 papers · 148 categories

Trend · papers per month

238477715953 · Jun 202019922001200920182026
48 results for Adaptive training

Adaptive networks improve model robustness through conditional normalization.

problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.

Enhances physics-informed neural networks with adaptive sampling and weighting.

problem Challenges in training physics-informed neural networks on complex problems.
method Hybrid adaptive sampling and weighting method.
result Consistently improves prediction accuracy and training efficiency.

Self-training improves gradual domain adaptation with unlabeled data.

problem Improving machine learning models' adaptability to gradually shifting data distributions.
method Proved upper bounds on self-training error, highlighted the importance of regularization and label sharpening, and demonstrated algorithmic insights.
result Self-training works well for gradual shifts, especially with small Wasserstein-infinity distance.

AdAdaGrad optimizes batch sizes for deep learning models, reducing the generalization gap.

problem The generalization gap between large-batch and small-batch training in deep learning.
method AdAdaGrad introduces adaptive batch size strategies derived from adaptive sampling methods.
result AdAdaGradNorm converges to a first-order stationary point with a rate of O(1/K) in K iterations.

Proposes blockwise adaptive stepsize for faster training and better generalization in deep learning.

problem Widespread use of coordinate-wise adaptive methods like RMSprop and Adam leads to worse generalization than SGD.
method Splits network parameters into blocks and uses a blockwise adaptive stepsize, balancing adaptivity and generalization.
result Blockwise adaptive gradient descent converges faster and has lower generalization error than coordinate-wise adaptive methods.

New algorithm closes the generalization gap of adaptive gradient methods in deep neural networks.

problem Generalization gap of adaptive gradient methods in training deep neural networks.
method Designing a new algorithm called Partially adaptive momentum estimation method (PAM) that unifies Adam/Amsgrad with SGD.
result Our proposed algorithm maintains fast convergence rates as Adam/Amsgrad while generalizing as well as SGD.

Aligns uncertainty predictions for domain adaptation using pre-trained deep networks.

problem Domain adaptation with unlabelled target data.
method Adversarial learning to align uncertainty predictions between source and target domains.
result Class prediction uncertainty on target domain matches source domain.

Adaptive batch size schedules improve language model training efficiency and generalization.

problem Dilemma of choosing batch sizes in large-scale model training.
method General-purpose adaptive batch size schedules compatible with data and model parallelism.
result Adaptive batch size schedules outperform constant batch sizes and heuristic warmup schedules.

New model-based methods adapt pre-trained policies to unseen environments efficiently.

problem High sample complexity in reinforcement learning limits practical applications.
method Combines online learning and adaptive control to adapt policies in unseen environments.
result Proves policies can quickly recover trajectories from source to target environments.

Improves deep neural network training and accuracy with adaptive basis approach.

problem Gap between theoretical and practical performance of deep neural networks.
method Adaptive basis viewpoint, novel initializations, hybrid optimizer.
result Dramatic increases in accuracy and convergence rate for various DNN applications.

Adaptive batch sizes improve local gradient methods in distributed training.

problem Communication bottlenecks in distributed deep learning.
method Adaptive batch size strategies for local gradient methods.
result Adaptive batch sizes reduce minibatch gradient variance and improve training efficiency.

AdaScale SGD adapts learning rates for large-batch training efficiently.

problem Adapting learning rates for large-batch training to balance speed-ups and model quality.
method Adaptive learning rate adaptation based on gradient variance.
result AdaScale achieves reliable speed-ups for a wide range of batch sizes without degrading model quality.

Adaptive methods often find worse generalization than SGD in overparameterized problems.

problem The performance of adaptive methods in overparameterized problems.
method Adaptive methods (AdaGrad, RMSProp, Adam) compared to gradient descent (GD) and stochastic gradient descent (SGD).
result Adaptive methods often generalize worse than SGD, even when they have better training performance.

New method AdaMod stabilizes deep neural network training by limiting adaptive learning rates.

problem Adaptive learning rates can produce extremely large values at the start of training, hindering learning.
method AdaMod uses adaptive and momental upper bounds to restrict learning rates dynamically.
result AdaMod eliminates large learning rates and improves training on complex networks.

This paper explains why Adam generalizes worse than SGD by analyzing its components.

problem Understanding why Adam generalizes worse than Stochastic Gradient Descent (SGD).
method Diffusion theoretical framework to disentangle the effects of Adaptive Learning Rate and Momentum.
result Adaptive Learning Rate helps escape saddle points but not select flat minima, while Momentum provides a drift effect to help pass through saddle points.

Discriminative active learning reduces data annotation costs for domain adaptation.

problem Conditional shift problem hinders domain adaptation between related but different domains.
method Three-stage active adversarial training: invariant feature space learning, uncertainty and diversity criteria, re-training with queried labels.
result Empirical comparisons show the proposed approach is more effective than existing methods.

Domain adaptation reduces prosthetic training time for amputees.

problem Reducing training time for non-invasive myoelectric prostheses.
method Evaluation of domain adaptation algorithms on amputee and intact subjects data.
result Previous experience from other subjects reduces training time by about an order of magnitude.

Paper introduces a new adaptive gradient method with gradient compression for distributed training.

problem Communication overhead in distributed machine learning systems.
method Adaptive gradient method with gradient compression, scalable system BytePS-Compress.
result Convergence rate of O(1/T)\mathcal{O}(1/\sqrt{T}) for non-convex problems.

Domain adaptation is the supervised learning setting in which the training and test data are sampled from different distributions: training data is sampled from a source domain, whilst test data is sampled from a target domain. This paper proposes and studies an approach, called feature-level domain adaptation (FLDA), …

2015-12-15abs ↗pdf ↗

Study on sparsity in CNNs trained with adaptive methods.

problem Understanding and optimizing sparsity in CNNs trained with adaptive methods.
method Experimental study of filter level sparsity in CNNs with BN and ReLU, using adaptive gradient descent and L2 regularization.
result Implicit sparsity can improve CNN performance and speedup without modifications.