arXiv research

Proposes first method for continuously indexed domain adaptation.

CoDAG combines domain adaptation and generalization for unsupervised continual domain shift learning.

Derives effective continuous dynamics for adaptive SGD methods.

This paper describes a reference architecture for self-maintaining systems that can learn continually, as data arrives. In environments where data evolves, we need architectures that manage Machine Learning (ML) models in production, adapt to shifting data distributions, cope with outliers, retrain when necessary, and …

Adaptive tensor modeling preserves continuity in multidimensional data.

We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions, while the other requires standard Lipschitz assumptions. Both bounds exhibit data-…

Paper analyzes convergence of continual learning with adaptive methods.

OSAMD adapts online to changing distributions with limited labels.

ADER addresses continual learning in session-based recommendation by periodically replaying exemplars with adaptive distillation.

Proposes a continuous, differentiable model from local adaptive models.

This paper tackles continuous domain adaptation with a new approach.

ReCAP adapts to dynamic financial markets by segmenting and combining policy vectors.

VCoTTA uses variational Bayesian methods to adapt models under continuous domain shifts.

AGS-CL selectively updates penalties based on node importance for continual learning.

An adaptive clustering algorithm learns from evolving data without manual tuning.

New algorithm improves online learning with reduced discretization.

Dropout has been proven to be an effective algorithm for training robust deep networks because of its ability to prevent overfitting by avoiding the co-adaptation of feature detectors. Current explanations of dropout include bagging, naive Bayes, regularization, and sex in evolution. According to the activation pattern…

LALR adapts learning rate for faster convergence in regression and neural nets.

New method prevents forgetting in LLMs by dynamically identifying task-specific subspaces.

SMART combines decision trees and MARS for better regression modeling.

BAM integrates new data while selectively remembering past observations.

Ada-BKB optimizes black-box functions on continuous domains with adaptive discretization.

Paper presents a method for efficient robot adaptation using fine-tuning.

New approach shows AI can adapt like toddlers by correcting old knowledge.

CAM-GAN improves GANs for continual learning with efficient feature map transformations.

The paper proposes a learning algorithm that improves adaptability and generalization.

A new buffer system improves continual learning in RL agents by adapting to changing environments.

We focus on the challenge of finding a diverse collection of quality solutions on complex continuous domains. While quality diver-sity (QD) algorithms like Novelty Search with Local Competition (NSLC) and MAP-Elites are designed to generate a diverse range of solutions, these algorithms require a large number of evalua…

CoLoRA models predict PDE solutions quickly and accurately with minimal data.

Optimal nonparametric regression estimator adapts to unknown smoothness.

We present the first PAC optimal algorithm for Bayes-Adaptive Markov Decision Processes (BAMDPs) in continuous state and action spaces, to the best of our knowledge. The BAMDP framework elegantly addresses model uncertainty by incorporating Bayesian belief updates into long-term expected return. However, computing an e…

Continual Learning is a learning paradigm where learning systems are trained with sequential or streaming tasks. Two notable directions among the recent advances in continual learning with neural networks are ($i$) variational Bayes based regularization by learning priors from previous tasks, and, ($ii$) learning the s…

ABHT boosts regression by filtering regions with different smoothness.

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…

Humans and animals can learn complex predictive models that allow them to accurately and reliably reason about real-world phenomena, and they can adapt such models extremely quickly in the face of unexpected changes. Deep neural network models allow us to represent very complex functions, but lack this capacity for rap…

Bayesian Federated Learning improves model reliability in dynamic environments.

AdaCat improves density estimation and planning in autoregressive models.

Learning and adapting to new distributions or learning new tasks sequentially without forgetting the previously learned knowledge is a challenging phenomenon in continual learning models. Most of the conventional deep learning models are not capable of learning new tasks sequentially in one model without forgetting the…

Local EGOP learns functions varying along a few directions.

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.

We adapt a Markov Random Field learning algorithm for continuous variables.

Algorithm adapts pretrained semantic segmentation models to new domains.

Adversarial online nonparametric regression achieves optimal rates with locally adaptive learning.

Novel Bayesian meta-reinforcement learning framework improves traffic signal control robustness.

Algorithm learns diffusion processes with high-dimensional state spaces.

Proposes CDTD, a diffusion model for mixed-type tabular data.