New analysis shows transfer learning can significantly reduce sample size for complex models.
problem Reducing sample size needed for complex models like large language models.
method Optimal transport viewpoint applied to analyze transfer learning efficiency.
result Transfer learning can achieve better sample efficiency for complex models.
With the help of transfer entropy, we analyze information flows between communities of complex networks. We show that the transfer entropy provides a coherent description of interactions between communities, including non-linear interactions. To put some flesh on the bare bones, we analyze transfer entropies between co…
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.
Hierarchical decoupling improves sample efficiency for complex robots.
problem Learning long-range behaviors on complex robots.
method Two-part policy: low-level imitation and high-level transfer, with KL regularization.
result Hierarchical transfer significantly improves zero-shot high-level transfer and stabilizes learning.
Transfer learning benefits vary in DRL, affecting representation and policy learning.
problem Understanding how much of DRL's sample complexity is due to representation learning.
method Transfer learning experiments comparing performance on related games.
result Benefits of transfer learning are highly variable and non-symmetric across tasks.
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.
Localized transfer learning improves nonparametric regression performance.
problem Improving nonparametric regression performance on target tasks.
method Localized transfer learning framework that models heterogeneity and partition covariate space into cells.
result Sharp minimax rates show local transfer mitigates the curse of dimensionality.
Gradient-based method prunes large models to create transferable architectures.
problem Creating transferable architectures from large models with limited fine-tuning data.
method Gradient-based algorithm for architecture pruning and subset selection.
result Successfully retrain architectures on new tasks with few fine-tuning data.
Transferring knowledge across a sequence of reinforcement-learning tasks is challenging, and has a number of important applications. Though there is encouraging empirical evidence that transfer can improve performance in subsequent reinforcement-learning tasks, there has been very little theoretical analysis. In this p…
Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained and transferred domains. The reconstruction of the original wiring for the target …
New statistical guarantees for transfer learning with diverse tasks.
problem Statistical guarantees for transfer learning across different tasks.
method Formal analysis of t+1 tasks with shared representation. result Sample complexity reduction for new tasks using shared representation.
Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample complexity of the new tasks. Considering that data collection in RL is both more time and cost consuming and Q-learning converge…
Measures neural network information transfer for generalization.
problem Estimating the generalizable information in neural networks.
method Proposes Information Transfer (LIT) based on prequential coding. result Consistently correlates with generalizable information in neural networks.
Transfer learning has been proven effective when within-target labeled data is scarce. A lot of works have developed successful algorithms and empirically observed positive transfer effect that improves target generalization error using source knowledge. However, theoretical analysis of transfer learning is more challe…
Transferability captures the ability of an attack against a machine-learning model to be effective against a different, potentially unknown, model. Empirical evidence for transferability has been shown in previous work, but the underlying reasons why an attack transfers or not are not yet well understood. In this paper…
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 O(1/ε2) for learning an ε-optimal policy. Calculates local Granger causality for Gaussian and nonlinear systems.
problem Understanding causal influence in complex systems.
method Vector autoregression and information-theoretic approach.
result Local Granger causality offers a robust and fast method for time-directed information transfer.
Paper proposes SOTL framework for improving transfer learning accuracy and efficiency.
problem Statistical bias and computational efficiency in multi-source domain adaptation.
method Sparse Optimization for Transfer Learning (SOTL) with L0-regularization.
result SOTL significantly improves estimation accuracy and computational speed, especially under adversarial conditions.
This paper provides a rational model for fiberwise THH transfer using A-infinity algebras.
problem Rational models for fiberwise THH transfer of fibrations over a base space.
method Explicit description of Hochschild homology transfer in terms of A-infinity algebras.
result Rational models for Becker-Gottlieb transfer and fiberwise THH-simple structures.
New unsupervised transfer learning method for spatiotemporal tasks.
problem Transfer knowledge from unsupervised models to new predictive tasks.
method Differentiable framework with Transferable Memory Unit (TMU).
result Significant improvements on spatiotemporal prediction benchmarks.
In complex transfer learning scenarios new tasks might not be tightly linked to previous tasks. Approaches that transfer information contained only in the final parameters of a source model will therefore struggle. Instead, transfer learning at a higher level of abstraction is needed. We propose Leap, a framework that …
Unified view on GP transfer learning for Bayesian optimization.
problem Improving data efficiency in Bayesian optimization with scarce data.
method Unified hierarchical GP models for transfer learning, including a novel boosted GP transfer model.
result Unified analysis and comparison of transfer learning methods for GP models.
This work shows how to use simulators to learn efficient exploration in real-world RL.
problem Sample complexity of real-world reinforcement learning.
method Coupling exploratory policies learned in simulators with practical approaches.
result Polynomial sample complexity in real world, exponential improvement over direct sim2real transfer.
A new boosting method reduces overfitting and negative transfer in transfer learning.
problem Overfitting and negative transfer in transfer learning.
method Importance sampling in boosting and random-forest based ensemble methodology.
result Performs better than competitive transfer learning methodologies 63% of the time.
A method for clustering using transfer learning from similar labeled data.
problem Clustering with datasets having different features and labeled data.
method Constructing meta-features to describe structural characteristics of data and transferring them between source and target domains.
result The method is efficient and works under arbitrary feature descriptions of source and target domains with smaller complexity.
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.
New algorithm reduces sample complexity for new tasks by leveraging prior knowledge.
problem Designing reinforcement learning agents that reduce sample complexity for new tasks.
method Designing an algorithm that quickly identifies an accurate solution by seeking informative state-action pairs from related tasks, using a generative model.
result PAC bounds on sample complexity demonstrate the benefits of using prior knowledge.
Knowledge Transfer (KT) techniques tackle the problem of transferring the knowledge from a large and complex neural network into a smaller and faster one. However, existing KT methods are tailored towards classification tasks and they cannot be used efficiently for other representation learning tasks. In this paper a n…
New method automates asymmetric choice for better skill transfer in reinforcement learning.
problem Improving sample efficiency and transferability of reinforcement learning agents.
method Attentive Priors for Expressive and Transferable Skills (APES) using hierarchical KL-regularization.
result APES automates asymmetric choice, leading to better skill transfer across sequential tasks.
In this paper we combine one method for hierarchical reinforcement learning - the options framework - with deep Q-networks (DQNs) through the use of different "option heads" on the policy network, and a supervisory network for choosing between the different options. We utilise our setup to investigate the effects of ar…
LOL-GP model improves surrogate modeling of expensive simulators.
problem Costly computer simulations for complex systems.
method Local transfer learning Gaussian process.
result Improved surrogate performance over existing methods.
Introduce a thermodynamically informed, temperature-transferable MLCG framework for proteins.
problem Temperature transferability of MLCG models for proteins.
method Explicit decomposition of CG potential into energetic and entropic components.
result Reproduces temperature-dependent quantities like heat capacity.
XMixup improves transfer learning accuracy by 1.9% with less training time.
problem Efficiently transfer knowledge from large source datasets to target tasks with small samples.
method Cross-domain Mixup technique that selects auxiliary samples from source datasets and augments training samples via mixup strategy.
result Improves accuracy by 1.9% on average over six real-world transfer learning datasets.
The paper studies practical estimation and interpretation of Rényi transfer entropy.
problem Challenges in accurately estimating and interpreting Rényi transfer entropy.
method Systematic study of k-nearest neighbor estimator for Rényi entropy and transfer entropy.
result Effective estimates of effective Rényi transfer entropy can accurately capture directional information flow.
New framework for RL transfer learning with state-action mismatch.
problem High sample complexity in RL from scratch.
method Embeddings to transfer knowledge between MDPs with different state- and action-spaces.
result Successful transfer learning in scenarios with state- and action-space mismatches.
We define a class of metrics that extend the Sasaki metric of a tangent manifold of a Riemannian manifold. The new metrics are obtained by the transfer of the generalized (pseudo-)Riemannian metrics of the pullback of the big tangent bundle of a manifold to the tangent manifold. We obtain the expression of the transfer…
This research evaluates learning models for bionic robots, focusing on transfer function identification.
problem Developers need guidance on selecting and constructing transfer functions for bionic robots.
method Comprehensive evaluation strategy including data collection, learning model selection, comparative analysis, and transfer function identification.
result A framework for effectively dealing with multi-input multi-output robotic data.
This work proposes a MFO framework for simultaneously evolving DQL models.
problem Complex DQL models struggle to converge to optimal policies due to exploration and sparse rewards.
method Combines meta-heuristic optimization, Transfer Learning, and DQL to automate knowledge transfer and policy learning.
result Framework automates knowledge transfer and policy learning of distributed RL agents.
New study reveals surprising adaptive rates in model selection for transfer learning.
problem Model selection in transfer learning with varying transfer distances.
method Theoretical analysis focusing on classification.
result Adaptive rates can be arbitrarily slower than oracle rates.
Paper tackles sim-to-real transfer in continuous domains with partial observations.
problem Lack of theoretical foundation for sim-to-real transfer in continuous domains with partial observations.
method Developed a new algorithm for infinite-horizon average-cost LQGs and established a regret bound.
result A popular robust adversarial training algorithm can learn competitive policies from simulation to real-world environments.
Behavior Transfer improves reinforcement learning by leveraging pre-trained policies.
problem Efficient transfer of knowledge in reinforcement learning.
method Behavior Transfer (BT) that uses pre-trained policies for exploration.
result BT combined with pre-training leads to better solutions than without pre-training.
Enhances VAR model estimation using transfer learning.
problem Estimating high-dimensional VAR models with temporal dependencies.
method Transfer learning for VAR models with low-rank and sparse structures.
result Theoretical guarantees for model parameter consistency and informative set selection.
Meta-Learning is a subarea of Machine Learning that aims to take advantage of prior knowledge to learn faster and with fewer data [1]. There are different scenarios where meta-learning can be applied, and one of the most common is algorithm recommendation, where previous experience on applying machine learning algorith…
Learning robot tasks or controllers using deep reinforcement learning has been proven effective in simulations. Learning in simulation has several advantages. For example, one can fully control the simulated environment, including halting motions while performing computations. Another advantage when robots are involved…
In this paper, we present a new approach to Transfer Learning (TL) in Reinforcement Learning (RL) for cross-domain tasks. Many of the available techniques approach the transfer architecture as a method of speeding up the target task learning. We propose to adapt and reuse the mapped source task optimal-policy directly …
A modular GP framework for efficient transfer learning.
problem Efficiently transfer knowledge across different tasks or datasets.
method Modular variational Gaussian processes (GPs) with a dictionary of well-fitted GPs.
result Reduces computational costs and allows the transfer of uncertainty metrics.
This paper introduces localized discrepancy theories for unsupervised domain adaptation.
problem Improving generalization bounds for unsupervised domain adaptation.
method Localized discrepancies defined on the hypothesis space after localization, leading to smaller and asymmetric values.
result Improved generalization bounds and sample complexity reduction.
Study reveals adversarially robust domain adaptation is harder to generalize across domains.
problem Hardness of transferring adversarial robustness across different domains.
method Analysis of adversarial Rademacher complexity over symmetric difference hypothesis space.
result Adversarial Rademacher complexity is always greater than non-adversarial, indicating intrinsic hardness.