Novel DCD-based algorithms improve RLS performance in noisy channels.
problem Improving recursive least squares performance in impulsive noise.
method Generalized DCD algorithm for RLS, robust strategies, variable forgetting factor.
result Unified update formula and improved tracking of abrupt changes.
New approach for deep neural networks to learn invariance through adversarial forgetting.
problem Learning invariance for deep neural networks in the presence of nuisance and bias factors.
method Adversarial forgetting mechanism to induce amnesia to unwanted data factors.
result State-of-the-art performance in learning invariance across various datasets and tasks.
New proof shows homomorphisms from pure braid groups to hyperbolic groups have cyclic images or factor through forgetful maps.
problem Characterizing homomorphisms from pure braid groups to hyperbolic groups.
method Extending and proving a new rigidity result for pure braid groups, focusing on homomorphisms to hyperbolic groups.
result Homomorphisms from pure braid groups to hyperbolic groups either have cyclic images or factor through a forgetful map.
We introduce the Kronecker factored online Laplace approximation for overcoming catastrophic forgetting in neural networks. The method is grounded in a Bayesian online learning framework, where we recursively approximate the posterior after every task with a Gaussian, leading to a quadratic penalty on changes to the we…
Paper analyzes trade-offs between static and dynamic regret in online learning.
problem Analyzing trade-offs between static and dynamic regret in online learning.
method Rigorously characterizes the effect of forgetting factors for online Newton algorithms and proposes a novel gradient descent step size rule.
result Achieves dynamic regret of max{O(log T), O(√TV)} for exp-concave and strongly convex objectives.
Study shows how task similarity affects forgetting in teacher-student setup.
problem Catastrophic forgetting in continual learning.
method Extended teacher-student setup to multiple teachers, analyzing similarity between tasks.
result Task similarity, whether at readouts or features, influences forgetting and transfer.
This work tackles catastrophic forgetting in neural networks by mimicking brain's metaplasticity.
problem Catastrophic forgetting in neural networks, where new tasks erase previously learned ones.
method Interpreting binarized neural networks as metaplastic systems, adjusting their training technique.
result Training technique reduces catastrophic forgetting without needing previously presented data.
Unified study of stateful replay for streaming learning, reducing forgetting by 2-3x.
problem Catastrophic forgetting in streaming generative and predictive learning.
method Unified analysis of stateful replay for autoencoding, forecasting, and classification tasks.
result Stateful replay reduces average forgetting by a factor of 2-3 on heterogeneous multi-task streams.
A Bayesian nonparametric approach for continual learning using neural networks.
problem Catastrophic forgetting in neural networks during sequential task settings.
method Indian Buffet Process (IBP) prior for dynamic model expansion and factorization of weight matrices.
result The method promotes positive knowledge transfer between tasks and allows for dynamic model complexity.
Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained. Reversible RNNs---RNNs for which the hidden-to-hidden transition can be reversed---offer a path to reduce the memory require…
New method speeds up lifelong learning of complex tasks.
problem Catastrophic forgetting in lifelong learning.
method Directly trains lifelong function approximators via policy gradients.
result Faster convergence and better policies achieved.
This paper tackles catastrophic forgetting in neural networks by providing a unified framework for regularization-based continual learning.
problem Catastrophic forgetting in neural networks trained sequentially on multiple tasks.
method Formulates regularization-based continual learning as a second-order Taylor approximation of the loss function, leading to a unified framework.
result Theoretical results indicate the importance of accurate approximation of the Hessian matrix for optimization and generalization.
The paper analyzes the efficiency of unlearning methods and establishes bounds for minimax computation times.
problem Efficiency of removing specific data points from a trained model without full retraining.
method Analysis of unlearning methods and establishment of upper and lower bounds on computation times.
result A phase diagram for the unlearning complexity ratio, revealing three regimes of feasibility.
Proposes a graph neural network for futures price prediction.
problem Challenges in high-frequency trading of futures prices.
method Heterogeneous Continual Graph Neural Network (STGNN) integrating multi-factor pricing theories.
result Outperforms other models in prediction accuracy on 49 commodity futures.
Study shows optimal model performance at critical level of feature learning.
problem Catastrophic forgetting in neural networks, especially in non-stationary environments.
method Systematic study on model scale and feature learning, using dynamical mean field theory.
result Optimal performance achieved at a critical level of feature learning, dependent on task non-stationarity and model scale.
Cluster analysis is used to explore structure in unlabeled data sets in a wide range of applications. An important part of cluster analysis is validating the quality of computationally obtained clusters. A large number of different internal indices have been developed for validation in the offline setting. However, thi…
Research shows continual learning challenges in confounded datasets.
problem Challenges in mitigating confounders in continual learning settings.
method Formal description of continual confounders, construction of ConCon dataset.
result Standard continual learning methods fail to ignore confounders.
Adam optimizer leads to more forgetting in neural networks.
problem Understanding and quantifying catastrophic forgetting in neural networks.
method Comparative analysis of various optimization algorithms and metrics in different learning scenarios.
result Adam optimizer causes more forgetting compared to classical algorithms like SGD.
We propose a methodology to explore and measure the pairwise correlations that exist between variables in a dataset. The methodology leverages copulas for encoding dependence between two variables, state-of-the-art optimal transport for providing a relevant geometry to the copulas, and clustering for summarizing the ma…
This paper investigates how forgetting affects neural network representations and stabilizes deeper layers.
problem Catastrophic forgetting in machine learning models trained on sequential tasks.
method Representational analysis techniques and empirical studies on CIFAR-10 and CIFAR-100 datasets.
result Deeper layers are disproportionately the source of forgetting, and methods to mitigate forgetting stabilize these layers.
New theory explains forgetting in learning algorithms.
problem Tendency of learning algorithms to forget past knowledge.
method Proposes a self-consistency theory of forgetting as a loss of predictive information.
result Exact Bayesian inference allows for adaptation without forgetting.
Spaced repetition is among the most studied learning strategies in the cognitive science literature. It consists in temporally distributing exposure to an information so as to improve long-term memorization. Providing students with an adaptive and personalized distributed practice schedule would benefit more than just …
The paper proposes selective forgetting for deep neural networks at a finer level than samples.
problem Selective forgetting of deep neural networks to handle outliers, poisoned data, or sensitive information.
method Formulated selective forgetting at a finer level than samples, introduced as an optimization problem on three criteria.
result Experimental results show the model can forget specific information for classification, improving accuracy in specific cases.
New copula models learn to forget dependencies, improving data representation.
problem Restrictive assumptions and poor scaling in existing copula models.
method Diffusion and flow-based copulas that progressively forget dependencies.
result Provable valid copulas at all times, superior performance in complex dependencies.
We discuss the relationship between the m-th homotopy group of the one-point union of r copies of the two-dimensional sphere and the m-th homotopy group of the one-point union of r+1 copies of the Thom space of the oriented two-dimensional universal vector bundle. Using a suitably choosen isomorphism between them a for…
Paper introduces Auto DeepVis to explain catastrophic forgetting in continual learning.
problem Catastrophic forgetting in continual learning of deep neural networks.
method Auto DeepVis and critical freezing techniques to address catastrophic forgetting.
result Critical freezing outperforms other methods on both past and future tasks.
The paper analyzes how forgetting in LLMs is linked to simple task-upstream example associations.
problem Forgetting of upstream knowledge in fine-tuned LLMs.
method Empirical analysis of forgotten examples in N upstream examples after M new tasks, using low-rank matrix approximation. result Forgetting can be predicted efficiently using matrix completion over empirical associations.
Discond-VAE separates continuous and discrete factors in data.
problem Separating shared and class-specific variations in real-world data.
method Introduces private and public latent variables to represent continuous and discrete factors, respectively.
result Discond-VAE successfully disentangles class-dependent continuous factors from discrete factors.
LoRA fine-tuning causes forgetting, studied via particle system dynamics.
problem Catastrophic forgetting in LoRA fine-tuning.
method Mean-field self-attention model, partial differential equations, dynamical systems.
result Characterization of phase transitions in forgetting behavior.
In this paper, we present our method of using fixed-size ordinally forgetting encoding (FOFE) to solve the word sense disambiguation (WSD) problem. FOFE enables us to encode variable-length sequence of words into a theoretically unique fixed-size representation that can be fed into a feed forward neural network (FFNN),…
Bayesian online meta-learning framework tackles catastrophic forgetting in few-shot classification.
problem Catastrophic forgetting in few-shot classification problems.
method Bayesian online learning, meta-learning, Laplace approximation, variational inference.
result Framework effectively achieves goal of overcoming catastrophic forgetting in few-shot classification.
Study analyzes catastrophic forgetting in continual learning using teacher-student networks.
problem Catastrophic forgetting in continuously learning systems.
method Teacher-student learning framework, similarity of input distributions and target functions.
result Network can avoid catastrophic forgetting with small input distribution similarity and large target function similarity.
Paper tackles catastrophic forgetting in sequential learning.
problem Catastrophic forgetting in sequential learning.
method Regularizes training with sketches of Jacobian matrix of past data.
result Proves overcoming catastrophic forgetting for linear and wide neural networks.
Overparameterization helps prevent forgetting in sequential learning tasks.
problem Catastrophic forgetting in continual learning systems.
method Analytical study of gradient descent with linear regression model.
result Overparameterization can mitigate forgetting in a two-task setting.
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.
Continual learning is hard for AI, leading to forgetting old knowledge.
problem Catastrophic forgetting in AI when learning new data.
method Review of continual learning in deep learning.
result Challenges and insights in continual learning.
Study examines how training regime affects neural networks' forgetting.
problem Catastrophic forgetting in neural networks when learning multiple tasks sequentially.
method Analyzes the impact of different training regimes (learning rate, batch size, regularization) on forgetting.
result Training regimes that widen tasks' local minima help prevent catastrophic forgetting.
A simple method to prevent forgetting in neural networks.
problem Catastrophic forgetting in neural networks.
method Weight friction, inspired by neurology and physics, modifies the gradient descent update rule.
result Weight friction enables continual learning with comparable performance and efficiency.
New insights into continual learning with task similarity.
problem Challenges in learning similar tasks without interference.
method Linear teacher-student model with latent structure.
result High input feature similarity with low readout similarity is catastrophic.
New homology categorifies knotoid polynomial.
problem Generalizing knot theory to open-ended diagrams.
method Defined winding homology as a triply-graded invariant.
result Categorifies Turaev's polynomial invariant of knotoids.
Hybrid framework prevents forgetting in continual learning.
problem Avoiding forgetting in learning new tasks without forgetting old ones.
method Hybrid continual learning framework combining architecture growth and experience replay.
result Hybrid approach effectively avoids forgetting across multiple tasks.
Adaptive model learns from time series data with changing distributions.
problem Predicting time series data under distribution shift.
method Formulates distribution shift as weighted empirical risk minimization. Uses a gradient-based learning method for a forgetting mechanism.
result Proposes an efficient method for adaptive time series prediction.
Study on neural networks forgetting in continual learning.
problem Forgetting in neural networks during continual learning.
method Gradient descent analysis on XOR-cluster datasets.
result Explicit bounds on forgetting rate and generalization gap.
In this paper, we show that Generative Adversarial Networks (GANs) suffer from catastrophic forgetting even when they are trained to approximate a single target distribution. We show that GAN training is a continual learning problem in which the sequence of changing model distributions is the sequence of tasks to the d…
Improves neural networks' ability to learn new tasks without forgetting earlier ones.
problem Preventing catastrophic forgetting in neural networks.
method Introducing a second discriminator in the GAN to generate important features for task retention.
result Significant reduction in catastrophic forgetting compared to standard methods.
Synthetic data helps prevent forgetting when learning sequentially.
problem Catastrophic forgetting in neural networks.
method Generate synthetic data via two-step optimisation process using meta-gradients.
result Training on synthetic data prevents forgetting when learning sequentially.
A wide class of machine learning algorithms can be reduced to variable elimination on factor graphs. While factor graphs provide a unifying notation for these algorithms, they do not provide a compact way to express repeated structure when compared to plate diagrams for directed graphical models. To exploit efficient t…
A new method prevents forgetting during knowledge transfer.
problem Catastrophic forgetting in transfer learning.
method Transfer without Forgetting (TwF) using a fixed pretrained network.
result TwF outperforms other CL methods by 4.81% in Class-Incremental accuracy.