OML learns representations to prevent forgetting in continual learning.
problem Continual learning agents forget existing knowledge when learning new data.
method OML directly minimizes catastrophic interference by learning representations that facilitate future learning.
result OML learns representations that accelerate future learning and are robust to forgetting.
OMBA learns product and user representations for better online market basket analysis.
problem Limited ability to uncover rarely occurring and temporal associations in MBA.
method Jointly learns product and user representations, captures temporal dynamics, scalable online method.
result OMBA outperforms state-of-the-art methods by 21% on real-world datasets.
Contrastive UCB improves RL by learning feature representations efficiently.
problem Improving feature learning in RL for online decision making.
method Proposes UCB-based contrastive learning algorithms for RL in MDPs and MGs.
result Proves sample efficiency in learning optimal policies and Nash equilibria.
Paper proposes a novel online transfer learning method to reduce domain discrepancy.
problem Online transfer learning with online distribution discrepancy minimization.
method The method seeks a new feature representation to simultaneously reduce marginal and conditional distribution discrepancies.
result The proposed method outperforms state-of-the-art methods in comprehensive experiments.
ReLEX algorithm improves RL efficiency by selecting optimal representations.
problem Improving reinforcement learning efficiency through better representation selection.
method Proposes ReLEX algorithm for both online and offline RL, focusing on bilinear transition kernels.
result ReLEX algorithms achieve optimal or near-optimal performance in both online and offline RL settings.
A new algorithm learns optimal source placement in large networks.
problem Optimizing source placement in large scale networks with unknown processes.
method Graph-Kernel Multi-Armed Bandit (Grab-UCB) algorithm with adaptive graph dictionary model.
result Online learning algorithm outperforms offline methods in terms of cumulative regret, sample efficiency, and computational complexity.
Prototype-based memory network learns visual categories from unlabeled data.
problem Learning from nonstationary, unlabeled data with sequential dependencies.
method Online prototype-based memory network with contrastive loss.
result Significantly better category recognition compared to state-of-the-art methods.
This work tackles representation learning for RL in low-rank MDPs, improving sample efficiency.
problem How to learn a compact representation for RL in low-rank MDPs efficiently.
method Proposes REP-UCB for online RL and develops an algorithm for offline RL under partial coverage.
result Significantly improved sample complexity for online RL and competitive performance for offline RL.
New method learns low-dimensional representations of AI-generated treatments.
problem Representing AI-generated treatments without losing semantic meaning.
method Double kernel representation learning with alternating minimization.
result Efficiently learned representations guide generative models and facilitate adaptive online experiments.
Wide and Deep GNN learns from distributed graphs and retrain online.
problem Decentralized graph support changes over time, causing mismatch between training and testing graphs.
method Wide and Deep GNN architecture with distributed online learning.
result Convergence guarantees for online retraining of the wide part of the GNN.
DeepCCG adapts classifiers to representation shifts in one step.
problem Adapting classifiers to shifts in continuous representation.
method Empirical Bayesian approach using class conditional Gaussian classifier and KL divergence for selection.
result DeepCCG reduces performance change due to representation shifts.
Unsupervised learning for evolving data streams with STAM architecture.
problem Learning from non-stationary, unlabeled data streams over time.
method Self-Taught Associative Memory (STAM) architecture with online clustering, novelty detection, and feature storage.
result STAM architecture improves clustering and classification tasks compared to existing continual learning models.
New algorithm REFUEL shows multitask representation learning is more sample-efficient in RL.
problem Understanding the benefit of representation learning in reinforcement learning.
method Developed REFUEL algorithm for multitask low-rank RL, analyzing both upstream and downstream tasks.
result Multitask representation learning is provably more sample-efficient than individual task learning.
ONN learns different representations for different operations to improve user response prediction.
problem Improving user response prediction in online advertising and recommendation systems.
method Proposes Operation-aware Neural Networks (ONN) to learn different representations for different operations.
result ONN consistently outperforms state-of-the-art models in both offline and online environments.
BYOL learns image representations without negative pairs.
problem Self-supervised image representation learning.
method Two neural networks interact and learn from each other, updating the target network with a slow-moving average of the online network.
result Achieves state-of-the-art performance on ImageNet.
PREREQ learns concept prerequisites from online educational resources.
problem Inferring prerequisite relations between educational concepts.
method PREREQ uses latent representations of concepts from Pairwise Latent Dirichlet Allocation and a Siamese neural network to learn from course prerequisites and labeled data.
result PREREQ outperforms state-of-the-art approaches and can learn from less data.
Residual Networks are shown to be equivalent to boosting feature representation.
problem Improving feature representation in deep learning models.
method Proved ResNet's equivalence to Online Gradient Boosting and proposed decision tree residual modules.
result ResNet can achieve Online Gradient Boosting regret bounds through architectural changes.
New method for online statistical inference in contextual bandits using SGD.
problem Online decision-making in contextual bandits with statistical inference.
method Weighted stochastic gradient descent for adaptive data collection.
result Asymptotic normality of the parameter estimator with improved efficiency.
This paper explores online learning of dynamics and state using ensemble Kalman filters.
problem Reconstructing dynamics from partial and noisy observations in real-time.
method Ensemble Kalman filter (EnKF) family of algorithms for online learning of dynamics and state.
result Demonstrates the efficiency and accuracy of online learning methods using Lorenz models.
SIGNNAP learns stable and identifiable node representations in GNNs against graph perturbations.
problem Fragility of GNN models to graph perturbations leading to unreliable node representations.
method SIGNNAP proposes a novel model that learns stable and identifiable node representations in an unsupervised manner, formalizing stability and identifiability through a contrastive objective and preserving smoothness with existing GNN backbones.
result SIGNNAP demonstrates effectiveness in learning stable and identifiable node representations in GNNs against graph perturbations on six benchmarks.
Paper proposes SDRL to improve continual learning with less computational cost.
problem Catastrophic forgetting in continual learning.
method SDRL method that refines gradients from memorized samples to reduce gradient diversity.
result SDRL shows better performance than state-of-the-art methods on multiple benchmark tasks.
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.
Neural network learns manifold structure for semi-supervised learning.
problem Semi-supervised learning on manifolds with explicit graph representations.
method Feed-forward neural network with two layers, learning manifold structure and classification.
result Neural network achieves semi-supervised learning on non-trivial manifolds.
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.
Improved online classification for manual material handling using wearable sensors.
problem Online monitoring of manual material handling activities using wearable sensors.
method Optimizes dictionary learning to improve sparse representation classification (SRC) accuracy and computational efficiency.
result Proposed method outperforms benchmark methods in accuracy and computational time for online monitoring.
Federated learning improves with adaptive hyper-parameters and representation matching.
problem Heterogeneous client data leads to divergent local models in federated learning.
method Representation matching and adaptive hyper-parameters.
result Significant performance and robustness improvements in federated learning.
In this paper, we focus on online representation learning in non-stationary environments which may require continuous adaptation of model architecture. We propose a novel online dictionary-learning (sparse-coding) framework which incorporates the addition and deletion of hidden units (dictionary elements), and is inspi…
Paper learns Koopman operator from sparse data, escaping function space constraints.
problem Learning Koopman operator from non-closed function spaces.
method Operator stochastic approximation algorithm using conditional mean embeddings (CME).
result Online sparse learning algorithm with trajectory-based sampling guarantees.
Metalearning optimizes autoencoder dimensions for efficient data representation.
problem Selecting optimal dimension for autoencoder output to balance accuracy and complexity.
method Metalearning approach using actor-critic algorithm to dynamically adjust dimension.
result Automatic selection of minimum number of bases for optimal reconstruction.
ProSMIN improves representation quality through probabilistic self-supervised learning.
problem Improving representation quality in self-supervised learning.
method ProSMIN uses two neural networks, online and target, to learn diverse representations through knowledge distillation and a modified scoring rule loss function.
result ProSMIN achieves superior accuracy and calibration on various downstream tasks.
Online random forests improve Q-learning performance in specific gym environments.
problem Improving Q-learning performance in reinforcement learning tasks.
method Proposed online random forests as Q-function approximators and growing them as learning progresses.
result Improved performance over state-of-the-art Deep Q-Networks in specific gym environments.
A scalable online method for Gaussian processes that improves decision-making in various applications.
problem Scalability issues with Gaussian processes for online decision-making.
method Online variational conditioning (OVC) for SVGPs.
result OVC enables efficient online learning and decision-making with SVGPs.
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.
We consider an online decision making setting known as contextual bandit problem, and propose an approach for improving contextual bandit performance by using an adaptive feature extraction (representation learning) based on online clustering. Our approach starts with an off-line pre-training on unlabeled history of co…
We propose a novel online learning algorithm for Restricted Boltzmann Machines (RBM), namely, the Online Generative Discriminative Restricted Boltzmann Machine (OGD-RBM), that provides the ability to build and adapt the network architecture of RBM according to the statistics of streaming data. The OGD-RBM is trained in…
An online algorithm improves cPCA for efficient, interpretable data analysis.
problem Efficiently finding informative low-dimensional representations in large datasets.
method Developed an online algorithm for a modified cPCA* method.
result The online algorithm for cPCA* shows improved performance and interpretability.
Convolutional sparse representations are a form of sparse representation with a structured, translation invariant dictionary. Most convolutional dictionary learning algorithms to date operate in batch mode, requiring simultaneous access to all training images during the learning process, which results in very high memo…
COLoKe adapts Koopman embeddings online, reducing overfitting and improving long-term predictions.
problem Online adaptation of Koopman embeddings to avoid overfitting and maintain long-term predictive accuracy.
method Combines deep feature learning with multistep prediction consistency in a lifted space, using a conformal-style mechanism for selective updates.
result Empirically effective in reducing overfitting and maintaining long-term predictive accuracy.
Online voting is an emerging feature in social networks, in which users can express their attitudes toward various issues and show their unique interest. Online voting imposes new challenges on recommendation, because the propagation of votings heavily depends on the structure of social networks as well as the content …
Mobile payment incentives optimized using merchant transaction networks.
problem Optimizing marketing campaigns with limited budgets.
method Graph representation learning on transaction networks.
result Effective modeling of merchant sensitivity to incentives.
This work examines a semi-blind single-channel source separation problem. Our specific aim is to separate one source whose local structure is approximately known, from another a priori unspecified background source, given only a single linear combination of the two sources. We propose a separation technique based on lo…
Gated Linear Networks bypass feature learning for fast online learning.
problem Fast online learning and feature learning trade-offs in neural networks.
method Distributed and local credit assignment mechanism, data-dependent gating, online convex optimization.
result GLNs achieve universal learning capabilities and resilience to catastrophic forgetting.
Paper develops robust policy evaluation for reinforcement learning with outlier and heavy-tailed rewards.
problem Outlier contamination and heavy-tailed rewards in reinforcement learning.
method Develops a fully online robust policy evaluation procedure and efficient statistical inference.
result Establishes the Bahadur-type representation of the estimator and develops an online inference procedure.
Since about 100 years ago, to learn the intrinsic structure of data, many representation learning approaches have been proposed, including both linear ones and nonlinear ones, supervised ones and unsupervised ones. Particularly, deep architectures are widely applied for representation learning in recent years, and have…
Survey categorizes methods for learning state representations in reinforcement learning.
problem Addressing challenges in complex observation spaces for sequential decision making.
method Categorizes six main classes of methods for learning state representations.
result Enhances understanding of state representation learning in reinforcement learning.
In this paper, we design a nonparametric online algorithm for estimating the triggering functions of multivariate Hawkes processes. Unlike parametric estimation, where evolutionary dynamics can be exploited for fast computation of the gradient, and unlike typical function learning, where representer theorem is readily …
The true online TD(λ) algorithm has recently been proposed (van Seijen and Sutton, 2014) as a universal replacement for the popular TD(λ) algorithm, in temporal-difference learning and reinforcement learning. True online TD(λ) has better theoretical properties than conventional TD(λ), and the expectation is that it als…
Improved transfer learning for MOOCs using auto-encoders.
problem Poor prediction performance of models trained on historical MOOC data.
method Automated transductive transfer learning with auto-encoders.
result Improved transferability of dropout prediction across similar and dissimilar MOOCs.