Transfer learning has been demonstrated to be successful and essential in diverse applications, which transfers knowledge from related but different source domains to the target domain. Online transfer learning(OTL) is a more challenging problem where the target data arrive in an online manner. Most OTL methods combine…
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.
168,695 papers · 148 categories
Trend · papers per month
48 results for “Online Transfer Learning”
Transfer learning techniques have been widely used in the reality that it is difficult to obtain sufficient labeled data in the target domain, but a large amount of auxiliary data can be obtained in the relevant source domain. But most of the existing methods are based on offline data. In practical applications, it is …
This paper explores how imperfect reward models can improve online RLHF.
problem Sample efficiency in online RLHF from imperfect reward models.
method Identifies policy coverability and proposes TPO algorithm for transfer learning.
result TPO algorithm improves sample efficiency compared to standard online learning.
Autonomous Vehicles(AV) are one of the brightest promises of the future which would help cut down fatalities and improve travel time while working in harmony. Autonomous vehicles will face with challenging situations and experiences not seen before. These experiences should be converted to knowledge and help the vehicl…
HySRL improves RL sample efficiency with shifted-dynamics data.
problem Leveraging historical data with shifted dynamics to improve sample efficiency in RL.
method HySRL, a hybrid transfer RL algorithm that uses prior information on dynamics shift to achieve better sample complexity.
result HySRL achieves problem-dependent sample complexity and outperforms pure online RL.
One-step Bellman alignment improves online RL by reducing task mismatch.
problem Online RL struggles with task similarity defined by rewards or transitions.
method One-step Bellman alignment and re-weighted targeting (RWT) to correct task mismatch.
result Regret bounds show task shift complexity, not target MDP, affects performance.
This paper tackles online strategic decision making with asymmetry and knowledge transportability.
problem Strategic decision making with information asymmetry and knowledge transportability challenges.
method Developed a sample-efficient algorithm for online learning under these conditions.
result Proved sample complexity of for learning an -optimal policy.
Paper shows pre-training and transfer learning reduce sample complexity for neural networks.
problem Training high-dimensional supervised learning with limited labeled data.
method Study of single-layer neural networks via online stochastic gradient descent, considering concept shift.
result Pre-training and transfer learning reduce sample complexity by polynomial factors under general assumptions.
Agent learns to trade currency pairs with improved risk management.
problem Improving systematic FX trading performance with online transfer learning.
method Online inductive transfer learning using feature representation from Gaussian mixture model to a reinforcement learning agent.
result Annualized portfolio information ratio of 0.52, compound return of 9.3%.
New method tackles anomaly detection in video surveillance using continual learning.
problem Challenges in continual learning for high-dimensional applications like video surveillance.
method Transfer learning and continual learning for online anomaly detection.
result Significantly reduces training complexity and continual learning from recent data.
Efficient transfer learning and online adaptation with latent variable models for continuous controlcs.LG
Traditional model-based RL relies on hand-specified or learned models of transition dynamics of the environment. These methods are sample efficient and facilitate learning in the real world but fail to generalize to subtle variations in the underlying dynamics, e.g., due to differences in mass, friction, or actuators a…
Transfer learning significantly accelerates the reinforcement learning process by exploiting relevant knowledge from previous experiences. The problem of optimally selecting source policies during the learning process is of great importance yet challenging. There has been little theoretical analysis of this problem. In…
The paper proposes an online algorithm for network resource allocation with reduced costs.
problem Optimizing resource allocation and job transfers in a network of servers.
method Randomized online algorithm based on the exponentially weighted method.
result The algorithm achieves sub-linear regret, indicating improved efficiency over time.
In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must rely on models trained from the historical data of previously offered courses. I…
Paper tackles robust knowledge transfer in parallel RL tasks.
problem Transfer knowledge from low-tier to high-tier tasks in parallel RL without shared dynamics or reward functions.
method Identifies Optimal Value Dominance condition and proposes online learning algorithms for both tasks.
result Achieves constant regret on partial states and near-optimal regret when tasks are dissimilar.
Learning from prior tasks and transferring that experience to improve future performance is critical for building lifelong learning agents. Although results in supervised and reinforcement learning show that transfer may significantly improve the learning performance, most of the literature on transfer is focused on ba…
Offline RL tackles resource-constrained online deployment with improved policy transfer.
problem Training policies with limited online features using a rich offline dataset.
method Introduce a policy transfer algorithm that first trains a teacher agent with full offline features and then transfers knowledge to a student agent with limited online features.
result Consistent improvement in performance over baseline methods on resource-constrained datasets.
Transferring knowledge across many streaming processes remains an uncharted territory in the existing literature and features unique characteristics: no labelled instance of the target domain, covariate shift of source and target domain, different period of drifts in the source and target domains. Autonomous transfer l…
Bayesian method improves multivariate periodontal outcome modeling.
problem Modeling periodontal outcomes is challenging and requires consideration of demographic differences.
method Jointly models multivariate outcomes using an online Bayesian transfer learning framework.
result Significant improvement over univariate RECaST method demonstrated.
Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrievalcs.LG
Improves search performance by transferring knowledge from recommender system.
problem Cold start and feedback loop problems in search retrieval.
method Zero-Shot Heterogeneous Transfer Learning framework.
result Significant improvements in relevance and user interactions over production system.
Simplifies transfer learning with deep neural networks using ridge regression.
problem High computational cost of finetuning deep models for transfer learning.
method Leverage the low-rank property of deep neural networks' feature vectors in kernel ridge regression.
result Successful on supervised and semi-supervised transfer learning tasks.
New method for efficient personalized learning in mobile health.
problem Efficient and personalized learning in mobile health.
method Proposes a novel generative process on kernel composition for online Gaussian Process regression.
result Trajectories of kernel evolutions can be transferred between users to improve learning and kernels are meaningful for mHealth prediction.
A TS algorithm improves performance in multi-task bandits with transfer.
problem Improving performance across multiple related bandit tasks.
method A TS-type algorithm for online multi-task learning with a novel concentration inequality.
result The TS-type algorithm achieves nearly-optimal performance guarantees.
MO2 learns useful behaviours from past experience for new tasks.
problem Discovering useful behaviours from past experience and transferring them to new tasks.
method Model-Based Offline Options (MO2) framework supporting sample-efficient bottleneck option discovery over continuous state-action spaces.
result MO2 outperforms recent option learning methods on complex long-horizon continuous control tasks.
Current reinforcement learning (RL) methods can successfully learn single tasks but often generalize poorly to modest perturbations in task domain or training procedure. In this work, we present a decoupled learning strategy for RL that creates a shared representation space where knowledge can be robustly transferred. …
Online Multi-Source Domain Adaptation through Gaussian Mixtures and Dataset Dictionary Learningcs.LG
Paper tackles online multi-source domain adaptation using Gaussian mixtures and dictionary learning.
problem Adapting multiple, heterogeneous source domains to a target domain in a streaming fashion.
method Introduces a novel approach for online fitting of Gaussian Mixture Models based on Wasserstein geometry, combined with dataset dictionary learning.
result Demonstrates ability to adapt 'on the fly' to target domain data streams.
Online learning rbfnet improves multi-horizon returns forecasts for financial time series.
problem Nonstationarity and concept drift in financial time series.
method Combines feature representation transfer with sequential optimisation.
result Online learning rbfnet outperforms random-walk and batch learners.
Model improves information transfer from visual streams.
problem Challenges in unsupervised learning from continuous visual data.
method Inspired by physics, maximizes mutual information through temporal process.
result Focus of attention enhances information transfer from input stream.
Paper tackles continuous transfer learning with evolving target domains.
problem Challenges of negative transfer in evolving target domains.
method Proposes label-informed C-divergence for measuring distribution shift and negative transfer.
result Demonstrates effectiveness of TransLATE framework in minimizing classification error and C-divergence.
Robot learns multiple tasks hierarchically by transferring knowledge.
problem Learning multiple complex tasks in open-ended environments.
method Task-oriented procedures, goal-babbling, imitation learning, active learning, intrinsic motivation.
result Robots can learn complex tasks more efficiently by transferring knowledge from simpler ones.
Guarantees for third-person imitation learning from offline data.
problem Improving generalizability in imitation learning.
method Problem-dependent statistical learning guarantees for third-person imitation from offline observation.
result Strong performance guarantees for transferred policies in the offline setting.
In this paper we address the problem of artist style transfer where the painting style of a given artist is applied on a real world photograph. We train our neural networks in adversarial setting via recently introduced quadratic potential divergence for stable learning process. To further improve the quality of genera…
A new framework for real-time multi-speaker diarization without prior registration.
problem Real-time multi-speaker diarization without prior registration and pretraining.
method Semi-supervised and self-supervised learning methods applied to a new benchmark.
result Robust performance in the online MiniVox framework.
Exponentially Weighted Algorithm for Online Network Resource Allocation with Long-Term Constraintsmath.OC
New algorithm optimizes online network resource allocation with long-term constraints.
problem Optimal resource reservation in communication networks with job transfers and budget limits.
method Randomized exponentially weighted method for long-term constraints.
result Upper bound for regret and cumulative constraint violations established.
Integrates multiple datasets to solve open set crowdsourcing problems.
problem Crowdsourcing with unknown label space and unfamiliar tasks.
method Integrates multiple crowdsourced datasets, weights them based on category correlation, and uses open set transfer learning.
result Proves OSCrowd solves open set crowdsourcing problems and outperforms related solutions.
In order to mimic the human ability of continual acquisition and transfer of knowledge across various tasks, a learning system needs the capability for continual learning, effectively utilizing the previously acquired skills. As such, the key challenge is to transfer and generalize the knowledge learned from one task t…
Model improves fraud detection for new scenes with limited data.
problem Improving fraud detection models with scarce training data.
method Adapted tree boosting for transfer learning.
result Enhanced model performance on new data.
Integrates skills and world models for efficient task solving and transfer.
problem Quickly solve new tasks in complex environments using reusable knowledge.
method Leverages partial amortization for fast adaptation and online skill planning.
result Improved sample efficiency in single tasks and transfer between tasks.
The study shows how modular learning can adapt to new tasks.
problem Adapting to new tasks in an ever-changing environment.
method Task segmentation, modular learning, memory-based ensembling.
result The system demonstrates robustness to catastrophic forgetting and increasing positive transfer.
We consider the problem of transfer learning in an online setting. Different tasks are presented sequentially and processed by a within-task algorithm. We propose a lifelong learning strategy which refines the underlying data representation used by the within-task algorithm, thereby transferring information from one ta…
We study the problem of meta-learning through the lens of online convex optimization, developing a meta-algorithm bridging the gap between popular gradient-based meta-learning and classical regularization-based multi-task transfer methods. Our method is the first to simultaneously satisfy good sample efficiency guarant…
Neural network tackles continual learning with neuromodulation and local error signals.
problem Catastrophic forgetting in continuous learning.
method Biologically-inspired neural architecture with local learning and neuromodulation, combined with transfer metalearning.
result Superior performance in continual learning tasks compared to other approaches.
Bilevel Continual Learning improves continual learning by transferring knowledge effectively.
problem Catastrophic forgetting and poor generalization in continual learning.
method Bilevel optimization and dual memory management strategies.
result BCL achieves effective knowledge transfer and alleviates catastrophic forgetting.
This work transfers fairness notions from binary classification to learning to rank.
problem Fairness concerns in automated ranking systems.
method Formalism to incorporate fairness objectives in learning to rank with provable guarantees.
result Improves ranking fairness substantially with minimal loss in model quality.
A new method for inventory control using in-context learning and generative models.
problem Inventory control with decision-dependent censoring, focusing on the censored newsvendor problem.
method In-context generative posterior sampling (ICGPS) combining modern generative models and in-context autoregressive generation.
result ICGPS achieves sublinear Bayesian regret for the censored newsvendor problem, outperforming existing methods.
Study shows pretraining and finetuning can effectively tackle covariate shift in linear regression.
problem Linear regression under covariate shift where source and target distributions differ but conditional distribution remains similar.
method Pretraining on source data and finetuning on target data using online SGD.
result Transfer learning with source data is as effective as supervised learning with target data.
Approaches to continual learning aim to successfully learn a set of related tasks that arrive in an online manner. Recently, several frameworks have been developed which enable deep learning to be deployed in this learning scenario. A key modelling decision is to what extent the architecture should be shared across tas…
New approach to continual learning prioritizes adaptation over retention.
problem Catastrophic forgetting in lifelong learning models.
method Formalized CL as an online optimization problem, introduced Transfer Efficiency, and derived a Critical Task Duration.
result Retention can hinder real-time adaptation in non-stationary environments.