arXiv research

New approach AR1 improves performance in class-incremental learning.

A new method for efficient CNN compression by incrementally assigning regularization factors to weights.

Proposes MEDIC to improve incremental learning by preventing forgetting and intransigence.

Autoencoder reduces memory overhead in incremental class learning.

Within a statistical learning setting, we propose and study an iterative regularization algorithm for least squares defined by an incremental gradient method. In particular, we show that, if all other parameters are fixed a priori, the number of passes over the data (epochs) acts as a regularization parameter, and prov…

Two new inverse-free ELM algorithms for incremental and decremental learning are proposed.

We analyze a fast incremental aggregated gradient method for optimizing nonconvex problems of the form $\min_x \sum_i f_i(x)$. Specifically, we analyze the SAGA algorithm within an Incremental First-order Oracle framework, and show that it converges to a stationary point provably faster than both gradient descent and s…

SupportNet tackles catastrophic forgetting in incremental learning with support data.

Proposes a probabilistic optimization method for large-scale problems.

A new generative classification strategy outperforms existing methods in class-incremental learning.

Data is continuously generated by modern data sources, and a recent challenge in machine learning has been to develop techniques that perform well in an incremental (streaming) setting. In this paper, we investigate the problem of private machine learning, where as common in practice, the data is not given at once, but…

Paper tackles incremental few-shot learning with novel classes.

Optimizes subset selection in sparse learning problems.

EVCL combines VCL and EWC to prevent forgetting new tasks.

CILF learns adaptive embeddings for class-incremental learning with novel class detection and model update.

Proposes a method to retrain neural networks incrementally for continuous data flow.

Transformers learn to integrate information from past positions incrementally, specializing heads in distinct patterns.

This paper investigates learning sparse representations and action-value functions simultaneously in deep reinforcement learning.

We study Nyström type subsampling approaches to large scale kernel methods, and prove learning bounds in the statistical learning setting, where random sampling and high probability estimates are considered. In particular, we prove that these approaches can achieve optimal learning bounds, provided the subsampling leve…

We propose an approach to reduce the bias of ridge regression and regularization kernel network. When applied to a single data set the new algorithms have comparable learning performance with the original ones. When applied to incremental learning with block wise streaming data the new algorithms are more efficient due…

Flashback Learning balances model stability and plasticity in continual learning.

DFI maps covariates to latent representations for feature importance.

FA algorithm provides convergence guarantees for deep linear networks.

We propose an inexact variable-metric proximal point algorithm to accelerate gradient-based optimization algorithms. The proposed scheme, called QNing can be notably applied to incremental first-order methods such as the stochastic variance-reduced gradient descent algorithm (SVRG) and other randomized incremental opti…

We introduce incremental variational inference and apply it to latent Dirichlet allocation (LDA). Incremental variational inference is inspired by incremental EM and provides an alternative to stochastic variational inference. Incremental LDA can process massive document collections, does not require to set a learning …

SAGA is a fast incremental gradient method on the finite sum problem and its effectiveness has been tested on a vast of applications. In this paper, we analyze SAGA on a class of non-strongly convex and non-convex statistical problem such as Lasso, group Lasso, Logistic regression with $\ell_1$ regularization, linear r…

We consider object recognition in the context of lifelong learning, where a robotic agent learns to discriminate between a growing number of object classes as it accumulates experience about the environment. We propose an incremental variant of the Regularized Least Squares for Classification (RLSC) algorithm, and expl…

SR improves learning speed in dynamic environments.

Paper introduces a new method for Gaussian Processes that improves prediction and hyper-parameter optimization.

This paper presents an asynchronous incremental aggregated gradient algorithm and its implementation in a parameter server framework for solving regularized optimization problems. The algorithm can handle both general convex (possibly non-smooth) regularizers and general convex constraints. When the empirical data loss…

A new algorithm for faster incremental kernel PCA and Nyström approximation.

The paper extends cluster validity indices for incremental analysis.

We describe novel subgradient methods for a broad class of matrix optimization problems involving nuclear norm regularization. Unlike existing approaches, our method executes very cheap iterations by combining low-rank stochastic subgradients with efficient incremental SVD updates, made possible by highly optimized and…

EILearn learns incrementally using previous classifier knowledge.

Paper proposes faster incremental subclass discriminant analysis.

Time and Sales of corn futures traded electronically on the CME Group Globex are studied. Theories of continuous prices turn upside down reality of intra-day trading. Prices and their increments are discrete and obey lattice probability distributions. A function for systematic evolution of futures trading volume is pro…

MetaCL enables neural networks to learn from small data streams without forgetting.

Enhances robustness of BLS using MCC criterion.

Depth helps neural networks learn simpler solutions incrementally.

SpaceNet improves continual learning by intelligently compressing neural connections.

Paper tackles few-shot class-incremental learning with a neural gas network.

Optimizes convergence rate of stochastic proximal algorithms for composite convex problems.

Regularization fails in continual learning tasks.

Large scale, streaming datasets are ubiquitous in modern machine learning. Streaming algorithms must be scalable, amenable to incremental training and robust to the presence of non-stationarity. In this work consider the problem of learning $\ell_1$ regularized linear models in the context of streaming data. In particu…

Deep Incremental Boosting speeds up Deep Learning training with improved generalization.

The FSRM uses a multifractional process to capture price multifractality, revealing serial information for forecasting.

A new model learns preferences incrementally without personal data.

Paper proposes CNE-net to tackle incremental learning in (T)ACSA tasks.