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

66131197262 · Jun 202019922001200920182026
48 results for adaptive reuse

ECPF improves classification accuracy and speed for evolving data streams.

problem Reusing classifiers trained on recurring concepts to maintain accuracy and speed.
method ECPF uses similarity of classifications to quickly identify the best classifier to reuse.
result ECPF significantly outperforms state-of-the-art frameworks on synthetic and real-world datasets.

Pipeline-aware hyperparameter tuning speeds up machine learning pipelines by reusing intermediate computations.

problem High computational burden in hyperparameter tuning of multi-stage pipelines.
method Proposes a hybrid hyperparameter tuning method and a caching problem formulated as an ILP to maximize reuse.
result Pipeline-aware approach offers over an order-of-magnitude speedup over independent evaluations.

Adaptive statistical learning improves model generalization with privacy-preserving techniques.

problem Overfitting and poor generalization in adaptive statistical learning.
method Adapting Bayesian differential privacy techniques to handle correlated data.
result The holdout dataset can be reused adaptively in statistical learning with privacy-preserving perturbations.

The paper investigates what enables successful transfer learning and separates feature reuse from data statistics.

problem Understanding what enables successful transfer learning and identifying the responsible parts of the network.
method Analyzes transfer learning on block-shuffled images to distinguish feature reuse from data statistics.
result Some benefit of transfer learning comes from learning low-level statistics of data, not just feature reuse.

KVCOMM optimizes multi-agent LLM systems by reusing KV-caches, reducing redundant processing.

problem Substantial overhead from reprocessing overlapping contexts across multi-agent systems.
method KVCOMM reuses KV-caches and adjusts offsets for shared content using a pool of cached examples (anchors).
result Achieves over 70% reuse rate across diverse multi-agent tasks, up to 7.8x speedup.

We introduce the Adaptive Skills, Adaptive Partitions (ASAP) framework that (1) learns skills (i.e., temporally extended actions or options) as well as (2) where to apply them. We believe that both (1) and (2) are necessary for a truly general skill learning framework, which is a key building block needed to scale up t…

2016-02-10abs ↗pdf ↗

Study on reliability of latent reuse in diffusion models under distribution shift.

problem When can latent spaces from a source dataset be reused for a target dataset with different distributions?
method Considered a source-target setting with approximately low-dimensional datasets near different subspaces. Analyzed the target-domain score error due to principal-angle misalignment and target ambient noise.
result Latent reuse is reliable only if the source and target subspaces are close and the target ambient noise is not too amplified.

Efficiently processes dynamic inputs in AI writing assistants with incremental computation.

problem Efficiently updating AI models in real-time with dynamic inputs.
method Incremental computing using vector quantization to filter and reuse intermediate values in neural networks.
result Comparable accuracy with 12.1X fewer operations for processing dynamic inputs.

Robotics learns new skills faster by reusing past movements.

problem Learning new motor skills is time-consuming and requires exploration of a large space of motor configurations.
method Combines probabilistic movement primitives with relative entropy policy search for skill initialization and adaptation.
result Quality of learned skills improves and the number of required iterations to learn a new task can be reduced by more than 60%.

New techniques reuse subword embeddings in neural models, reducing size and improving performance.

problem Improving performance and reducing model size in subword-aware neural language models.
method Reusing subword embeddings and other weights in multi-layer input embedding models, tying layers consecutively bottom-up.
result Best morpheme-aware model with reused weights outperforms competitive word-level model by a large margin.

Framework learns best model from diverse pretrained models for distribution shift.

problem No single pretrained model is best for all downstream tasks under distribution shift.
method Frontier Learning constructs a unified feature from white-box and black-box models, fitting a lightweight learner.
result Frontier Learning matches or outperforms strongest individual reuse strategy across settings.

Bayesian Experience Reuse improves learning from multiple experts.

problem Learning from multiple experts with conflicting goals.
method Bayesian neural networks with shared features to model uncertainty and derive a probability distribution over expert models.
result BERS method effectively samples demonstrations from the derived distribution to reuse them in new tasks.

Self-organizing maps improve reinforcement learning efficiency.

problem Improving sample efficiency in reinforcement learning.
method Using a similarity measure based on self-organizing maps to store and transfer knowledge between tasks.
result The approach significantly improves sample efficiency in reinforcement learning.

New method reduces bias in high-dimensional action spaces for efficient reinforcement learning.

problem Large bias and difficulty in reusing old samples in high-dimensional action spaces.
method Dimension-wise IS weight clipping to control bias and adaptively manage IS weights.
result Proposed method outperforms PPO and other RL algorithms in various tasks.

DTS improves inference-time alignment of diffusion models with less compute.

problem Inference-time alignment of diffusion models suffers from inaccurate value estimation and inefficient reuse of past computations.
method Diffusion Tree Sampling (DTS) uses a tree-based approach to propagate terminal rewards and iteratively refine value estimates.
result DTS produces asymptotically exact samples and matches the FID of best-performing baselines with up to 10x less compute.

AdapVAE learns streaming data clustering and feature learning adaptively.

problem Adaptive clustering and feature learning for streaming data.
method Bayesian Nonparametric (BNP) modeling with Deep Neural Networks (DNNs) for feature learning, online variational inference algorithm.
result AdapVAE can adaptively detect novel clusters in emerging data without catastrophic forgetting.

Adapts data analysis for growing data, improving generalization guarantees.

problem Challenges of overfitting and statistical validity in adaptive workflows with growing data.
method Generalizes adaptive analysis on dynamic data, incorporating time-varying empirical accuracy bounds and mechanisms.
result First generalization bounds for adaptive analysis on dynamic data, matching prior works' improvement over data splitting.

Paper proposes PRR network for better experience reuse in reinforcement learning.

problem Efficient experience reuse in reinforcement learning across multiple granularities.
method Proposes PRR network trained on multi-level architecture to extract and store experience.
result PRR network leads to better experience reuse and improved performance.

FLAP adapts policies quickly to new tasks using shared linear representations.

problem Adapting policies to new tasks efficiently and effectively.
method FLAP uses a shared linear representation and a separate adapter network for quick adaptation.
result FLAP achieves up to 8X faster adaptation and significantly better performance on out-of-distribution tasks.

Improved scaling laws in linear regression using data reuse.

problem Sustainability of neural scaling laws when running out of new data.
method Data reuse in multi-pass stochastic gradient descent (multi-pass SGD) for MM-dimensional linear models trained on NN data with sketched features.
result Multi-pass SGD achieves a test error of Θ(M1b+L(1b)/a)Θ(M^{1-b} + L^{(1-b)/a}) with L>NL>N, improving scaling laws in data-constrained regimes.

New method uses rank-conditioned Horvitz-Thompson estimation for unbiased sample reuse in Plackett-Luce best-of-K objective.

problem Estimating the expected maximum reward in Plackett-Luce draws without replacement.
method Rank-conditioned Horvitz-Thompson estimation with joint-score REINFORCE for unbiased sample reuse.
result Unbiased estimation of the Plackett-Luce best-of-K objective with finite second moment guarantees.

The paper proposes a uniformity regularization scheme to improve deep neural network transferability.

problem Improving deep neural network transferability and adaptation to new tasks.
method Introduces a uniformity regularization scheme to encourage high uniformity in embedding space.
result Uniformity regularization consistently offers benefits over baseline methods and achieves state-of-the-art performance in Deep Metric Learning and Meta-Learning.

ACS is an interactive framework for model-free selection with guaranteed error control.

problem Model-free selection with rigorous error control.
method Adaptive conformal selection with human-in-the-loop data exploration and new information incorporation.
result ACS provides concrete selection algorithms for various goals, including model update/selection, diversified selection, and incorporating new data.

Method predicts rarity of image features to support research integrity investigations.

problem Difficulty in determining if image reuse is by chance or intentional.
method Statistical estimation of ORB features' chance occurrence across PubMed Open Access Subset dataset.
result The method produces decreasingly smaller p-values for more complex imagery, supporting null hypothesis.

Differentially private algorithms protect model explanations from leaking training data.

problem Model explanations can leak training data, compromising privacy.
method Adaptive differentially private gradient descent algorithm to produce accurate, private explanations.
result Privacy amplification and reduction of overall privacy loss on explanation data.

CLEAS improves neural architecture search for continual learning.

problem Overcoming catastrophic forgetting and adapting to new tasks while controlling model complexity.
method Neural architecture search (NAS) with reinforcement learning to find optimal neural architecture.
result CLEAS achieves higher classification accuracy with simpler neural architectures.

Improved Markov models learn from their mistakes and adapt to problem complexity.

problem Limitations of standard masked discrete diffusion models in reasoning tasks.
method Learning a Markov transition kernel trained on its own outputs, allowing remasking and adaptation.
result Significant improvement in solving reasoning problems, especially Sudoku-Extreme and Countdown-4.