Proposes first method for continuously indexed domain adaptation.
problem Challenges of transferring knowledge between continuously indexed domains.
method Combines adversarial adaptation with a novel discriminator.
result Outperforms state-of-the-art methods on synthetic and real-world datasets.
The paper tackles contextual bandits with continuous actions using smoothing and zooming techniques.
problem Learning with continuous action spaces in the context of contextual bandits.
method The approach involves smoothing and zooming techniques to handle the continuous action space and unknown smoothness parameters.
result Improved regret bounds and adaptive algorithms for contextual bandits with continuous actions.
CoDAG combines domain adaptation and generalization for unsupervised continual domain shift learning.
problem Acquiring knowledge in unsupervised continual domain shift learning.
method Complementary Domain Adaptation and Generalization (CoDAG) framework.
result CoDAG outperforms state-of-the-art models in all datasets and evaluation metrics.
Paper outlines a system for ML models to learn continuously from evolving data.
problem Managing ML models in environments where data evolves.
method Describes a reference architecture for self-maintaining systems.
result Proposes a reference architecture for continual AutoML.
Derives effective continuous dynamics for adaptive SGD methods.
problem Analyzing noise in adaptive SGD methods.
method Stochastic modified equations framework and Malladi's scaling rules.
result Sampling-induced noise in SGD limits to independent Brownian motions.
Adaptive tensor modeling preserves continuity in multidimensional data.
problem Discretization of continuous multidimensional data loses important information.
method Functional Tucker decomposition (FTD) with RKHS modeling.
result FTD enables adaptive and expressive tensor modeling.
Paper analyzes convergence of continual learning with adaptive methods.
problem Preventing catastrophic forgetting in sequential learning tasks.
method Adaptive method for nonconvex continual learning (NCCL) adjusts step sizes of previous and current tasks.
result Proposed adaptive method achieves same convergence rate as SGD when catastrophic forgetting is suppressed.
Bayesian approach adapts deep network structure for continual learning.
problem Training neural networks with sequential or streaming tasks.
method Bayesian approach to learn deep network structure for each task.
result Model performs comparably or better than recent advances in continual learning.
OSAMD adapts online to changing distributions with limited labels.
problem Models struggle with continual distribution shifts and expensive labeling in changing environments.
method Online Active Continual Adaptation with OSAMD, an online teacher-student structure and margin-based criterion.
result OSAMD achieves favorable dynamic regret bounds under changing environments with limited labels.
ADER addresses continual learning in session-based recommendation by periodically replaying exemplars with adaptive distillation.
problem Catastrophic forgetting in continual learning of session-based recommenders.
method Periodically replaying previous training samples (exemplars) with an adaptive distillation loss.
result ADER consistently outperforms other continual learning techniques and even all historical data at every update cycle.
Proposes a continuous, differentiable model from local adaptive models.
problem Inadequate continuity and differentiability in over-parameterized models.
method A global continuous and differentiable model constructed from weighted averages of locally learned models.
result Achieves faster statistical convergence and improved performance in various settings.
This paper tackles continuous domain adaptation with a new approach.
problem Learning in non-stationary environments, especially domain drift.
method Variational domain-agnostic feature replay, composed of inference, generative, and solver modules.
result Demonstrates the effectiveness of the proposed approach for practical usage.
ReCAP adapts to dynamic financial markets by segmenting and combining policy vectors.
problem Inefficient traditional PM approaches in non-stationary financial markets.
method Integrates continual learning into PM, segmenting regimes and adapting policies.
result Consistently outperforms baselines in real-world financial datasets.
VCoTTA uses variational Bayesian methods to adapt models under continuous domain shifts.
problem Error accumulation in continual test-time adaptation.
method VCoTTA employs variational Bayesian techniques to update a Bayesian Neural Network (BNN) during testing, combining priors from source and teacher models.
result VCoTTA effectively mitigates error accumulation in CTTA, as shown by experimental results on three datasets.
CLAW adapts weights to balance continual learning and catastrophic forgetting.
problem Balancing continual learning across multiple tasks without forgetting previous knowledge.
method Probabilistic modelling and variational inference to adaptively share network components.
result CLAW achieves state-of-the-art performance in continual learning benchmarks.
AGS-CL selectively updates penalties based on node importance for continual learning.
problem Catastrophic forgetting in continual learning.
method Adaptive Group Sparsity (AGS) with proximal gradient descent.
result Significantly outperforms baselines on various continual learning benchmarks.
Continuous dropout mimics brain neuron firing rates to prevent feature detector co-adaptation.
problem Preventing overfitting in deep neural networks.
method Extending binary dropout to continuous dropout, inspired by brain neuron firing rates.
result Continuous dropout improves test performance by preventing feature detector co-adaptation.
An adaptive clustering algorithm learns from evolving data without manual tuning.
problem Clustering in dynamic data environments where distributions change over time.
method ART-based topological clustering with self-adjusting vigilance parameter.
result The algorithm outperforms state-of-the-art methods in clustering performance and continual learning.
New algorithm improves online learning with reduced discretization.
problem Improving adaptive online learning with refined discretization.
method Continuous time approach to online learning, followed by a new discretization argument.
result Optimal regret bound with O ( V T ) O(\sqrt{V_T}) O ( V T ) dependence on gradient variance. CMA-ME combines CMA-ES and MAP-Elites for better quality and diversity in continuous domains.
problem Finding a diverse set of high-quality solutions in complex continuous domains.
method Combines CMA-ES self-adaptation with MAP-Elites archiving and mapping.
result CMA-ME outperforms MAP-Elites in both quality and diversity of solutions.
Adaptive Quantization Modules enable online continual compression of non-i.i.d data streams.
problem Learning to compress and store a dataset from a non-i.i.d data stream, only observing each sample once.
method Discrete auto-encoders and Adaptive Quantization Modules (AQM) to control compression ability.
result Significant gains on continual learning benchmarks with AQM replacing episodic memory.
LALR adapts learning rate for faster convergence in regression and neural nets.
problem Finding optimal learning rates for faster convergence in regression and neural networks.
method Lipschitz continuity theory applied to Mean Absolute Error and Quantile loss functions.
result Adaptive learning rate policy enables up to 20x faster convergence.
New method prevents forgetting in LLMs by dynamically identifying task-specific subspaces.
problem Catastrophic forgetting in continual learning of LLMs.
method Adaptive Singular Value Decomposition (SVD) for constrained full fine-tuning.
result Achieves state-of-the-art results in continual learning benchmarks.
SMART combines decision trees and MARS for better regression modeling.
problem High variance in decision trees for continuous relationships, poor performance in MARS for discontinuities.
method SMART uses a decision tree to identify subsets with distinct continuous relationships, then applies MARS to fit these relationships independently.
result SMART improves regression performance over state-of-the-art methods in capturing discontinuities and continuous relationships.
Paper develops a method for rapid online learning of deep models.
problem Rapid adaptation of deep models to changing tasks.
method Uses meta-learning to train a model that can adapt to new tasks and recall old ones.
result Meta-learning enables effective continuous adaptation in non-stationary task distributions.
BAM integrates new data while selectively remembering past observations.
problem Slow adaptation and convergence to incorrect parameter values in non-stationary environments.
method Bayes' theorem with adaptive memory selection.
result BAM generalizes and demonstrates continuous adaptation in changing environments.
Ada-BKB optimizes black-box functions on continuous domains with adaptive discretization.
problem Optimizing functions with continuous domains using Gaussian process optimization.
method Adaptive discretization of the function domain to avoid non-convex optimization costs.
result Ada-BKB algorithm runs in O ( T 2 d e x t e f f 2 ) O(T^2 d_ ext{eff}^2) O ( T 2 d e x t e f f 2 ) , significantly faster than existing methods. Adapts to new environments in robotics using latent variable models.
problem Learning dynamics in robotic environments with subtle variations.
method Variational inference for latent representation, online Bayesian inference, neural network ensemble.
result Positive transfer during training and online adaptation on HalfCheetah task.
Paper presents a method for efficient robot adaptation using fine-tuning.
problem Continuous adaptation of robot learning systems in real-world scenarios.
method Fine-tuning previously learned policies using off-policy reinforcement learning.
result Fine-tuning leads to substantial performance gains and adaptation to new conditions.
New approach shows AI can adapt like toddlers by correcting old knowledge.
problem Lack of adaptability in AI models compared to humans and animals.
method Casting adaptation as posterior correction and using Bayesian Learning Rule.
result AI can learn to adapt quickly by using posterior correction.
CAM-GAN improves GANs for continual learning with efficient feature map transformations.
problem Efficient continual learning for GANs with reduced parameter growth.
method Designing and leveraging parameter-efficient feature map transformations, including global and task-specific parameters, residual bias, and Fisher information matrix.
result Significantly improved model performance and high-quality samples with fewer parameters.
A Kalman Optimiser improves continual learning in deep neural networks.
problem Learning new tasks sequentially without forgetting previously learned knowledge.
method Divides the neural network into long-term and short-term memory units.
result The method enables continual learning and adaptation without forgetting.
Bayes-CPACE optimally explores continuous BAMDPs.
problem Model uncertainty in continuous state and action spaces.
method Covering state-belief-action space with samples, exploiting Lipschitz continuity.
result Near-optimal value function computed efficiently.
The paper proposes a learning algorithm that improves adaptability and generalization.
problem Improving adaptability and generalization in learning models.
method Learning to meta-learn by meta-finetuning on related tasks before adapting to specific tasks.
result Learning to meta-learn improves adaptability and generalization across various tasks.
A new buffer system improves continual learning in RL agents by adapting to changing environments.
problem Improving RL agents' ability to learn from changing environments over time.
method Multi-timescale replay buffer combined with invariant risk minimization.
result The method shows improvement over baselines in continual learning settings.
CoLoRA models predict PDE solutions quickly and accurately with minimal data.
problem Efficiently modeling PDE solutions with limited data.
method Continuous low-rank adaptation of neural networks trained on offline data.
result Predictions are orders of magnitude faster and more accurate than classical methods.
Optimal nonparametric regression estimator adapts to unknown smoothness.
problem Nonparametric regression with unknown smoothness.
method Constructs an interpolating estimator that adapts to unknown smoothness.
result Minimax optimal rates achieved on Hölder classes.
ABHT boosts regression by filtering regions with different smoothness.
problem Improving regression performance through local adaptivity.
method Gradient boosting with adaptive histogram transform.
result ABHT converges faster than PEHT in Hölder continuous spaces.
Continuous appearance shifts such as changes in weather and lighting conditions can impact the performance of deployed machine learning models. While unsupervised domain adaptation aims to address this challenge, current approaches do not utilise the continuity of the occurring shifts. In particular, many robotics appl…
We develop the method of stochastic modified equations (SME), in which stochastic gradient algorithms are approximated in the weak sense by continuous-time stochastic differential equations. We exploit the continuous formulation together with optimal control theory to derive novel adaptive hyper-parameter adjustment po…
Bayesian Federated Learning improves model reliability in dynamic environments.
problem Uncertainty quantification and robust adaptation in distributed learning.
method Proposes a continual BFL framework using SGLD for sequential updates and continual learning challenges.
result Continual Bayesian updates preserve knowledge and adapt to evolving data.
AdaCat improves density estimation and planning in autoregressive models.
problem Efficiently modeling sharp density changes in continuous data.
method Adaptive Categorical Discretization (AdaCat) for autoregressive models.
result Improves density estimation and planning in various data types.
Local EGOP learns functions varying along a few directions.
problem Efficient estimation of functions varying along a few directions in high-dimensional space.
method Local EGOP learning, a recursive algorithm using EGOP quadratic form as metric and inverse-covariance.
result Local EGOP learning achieves intrinsic dimensional learning rates under noisy manifold hypothesis.
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.
We adapt a Markov Random Field learning algorithm for continuous variables.
problem Learning sparse pairwise Markov Random Fields with continuous variables.
method Adapted Vuffray et al. (2019) algorithm for continuous variables and provided analysis.
result Sample complexity scales logarithmically with the number of variables.
New method for adaptive sensor placement in continuous spaces reduces detection error.
problem Adaptive sensor placement for detecting stochastic events in continuous intervals.
method Combining Thompson sampling with nonparametric inference via Bayesian histograms.
result Derives an O ( T 2 / 3 ) O(T^{2/3}) O ( T 2/3 ) bound on Bayesian regret, demonstrating efficiency in simulations. Algorithm adapts pretrained semantic segmentation models to new domains.
problem Adapting pretrained models to new, unlabeled domains without source data.
method Learn prototypical distribution in embedding space, align target domain with source domain.
result Method achieves competitive performance on benchmark tasks.
Efficient algorithm for reinforcement learning in large state-action spaces with adaptive discretization.
problem Efficient reinforcement learning in large, potentially continuous state-action spaces.
method Adaptive Q Q Q -learning policy with data-driven adaptive discretization. result Demonstrates improved performance compared to existing methods, especially in adapting to the problem's structure.