English
Related papers

Related papers: Does the Adam Optimizer Exacerbate Catastrophic Fo…

200 papers

The innate capacity of humans and other animals to learn a diverse, and often interfering, range of knowledge and skills throughout their lifespan is a hallmark of natural intelligence, with obvious evolutionary motivations. In parallel,…

Machine Learning · Computer Science 2021-12-30 David McCaffary

A key stepping stone in the development of an artificial general intelligence (a machine that can perform any task), is the production of agents that can perform multiple tasks at once instead of just one. Unfortunately, canonical methods…

Neural and Evolutionary Computing · Computer Science 2019-04-08 Joseph Early

Catastrophic forgetting in neural networks during incremental learning remains a challenging problem. Previous research investigated catastrophic forgetting in fully connected networks, with some earlier work exploring activation functions…

Machine Learning · Computer Science 2023-03-15 Jiahao Huo , Terence L. van Zyl

Contrary to common belief, we show that gradient ascent-based unconstrained optimization methods frequently fail to perform machine unlearning, a phenomenon we attribute to the inherent statistical dependence between the forget and retain…

Machine Learning · Computer Science 2025-10-20 Ioannis Mavrothalassitis , Pol Puigdemont , Noam Itzhak Levi , Volkan Cevher

The problem of a deep learning model losing performance on a previously learned task when fine-tuned to a new one is a phenomenon known as Catastrophic forgetting. There are two major ways to mitigate this problem: either preserving…

Computer Vision and Pattern Recognition · Computer Science 2019-07-24 Shivangi Srivastava , Maxim Berman , Matthew B. Blaschko , Devis Tuia

The adaptive moment estimation (Adam) optimizer proposed by Kingma & Ba (2014) is presumably the most popular stochastic gradient descent (SGD) optimization method for the training of deep neural networks (DNNs) in artificial intelligence…

Machine Learning · Computer Science 2026-03-20 Steffen Dereich , Thang Do , Arnulf Jentzen

In continual learning, a system learns from non-stationary data streams or batches without catastrophic forgetting. While this problem has been heavily studied in supervised image classification and reinforcement learning, continual…

Artificial Intelligence · Computer Science 2021-04-20 Tyler L. Hayes , Christopher Kanan

Continual learning (CL) enables animals to learn new tasks without erasing prior knowledge. CL in artificial neural networks (NNs) is challenging due to catastrophic forgetting, where new learning degrades performance on older tasks. While…

Machine Learning · Computer Science 2025-01-28 Haozhe Shan , Qianyi Li , Haim Sompolinsky

Forgetting is often seen as an unwanted characteristic in both human and machine learning. However, we propose that forgetting can in fact be favorable to learning. We introduce "forget-and-relearn" as a powerful paradigm for shaping the…

Machine Learning · Computer Science 2022-02-02 Hattie Zhou , Ankit Vani , Hugo Larochelle , Aaron Courville

Continual learning of partially similar tasks poses a challenge for artificial neural networks, as task similarity presents both an opportunity for knowledge transfer and a risk of interference and catastrophic forgetting. However, it…

Machine Learning · Statistics 2024-05-31 Naoki Hiratani

Catastrophic forgetting remains a fundamental challenge in continual learning for large language models. Recent work revealed that performance degradation may stem from spurious forgetting caused by task alignment disruption rather than…

Machine Learning · Computer Science 2025-12-25 Weiwei Wang

We study the issue of catastrophic forgetting in the context of neural multimodal approaches to Visual Question Answering (VQA). Motivated by evidence from psycholinguistics, we devise a set of linguistically-informed VQA tasks, which…

Computation and Language · Computer Science 2019-06-12 Claudio Greco , Barbara Plank , Raquel Fernández , Raffaella Bernardi

Recent advances in Large Language Models (LLMs) have exhibited remarkable proficiency across various tasks. Given the potent applications of LLMs in numerous fields, there has been a surge in LLM development. In developing LLMs, a common…

Computation and Language · Computer Science 2024-01-09 Chen-An Li , Hung-Yi Lee

Supervised Fine-Tuning (SFT) is a critical step for enhancing the instruction-following capabilities of Large Language Models (LLMs) and adapting them to specialized domains. However, SFT often leads to a degradation of the model's general…

Computation and Language · Computer Science 2025-07-01 Fei Ding , Baiqiao Wang

Matching animal-like flexibility in recognition and the ability to quickly incorporate new information remains difficult. Limits are yet to be adequately addressed in neural models and recognition algorithms. This work proposes a…

Computer Vision and Pattern Recognition · Computer Science 2012-06-26 Tsvi Achler

We investigate the effect of task ordering on continual learning performance. We conduct an extensive series of empirical experiments on synthetic and naturalistic datasets and show that reordering tasks significantly affects the amount of…

Machine Learning · Computer Science 2022-05-27 Samuel J. Bell , Neil D. Lawrence

While recent continual learning methods largely alleviate the catastrophic problem on toy-sized datasets, some issues remain to be tackled to apply them to real-world problem domains. First, a continual learning model should effectively…

Machine Learning · Computer Science 2020-02-18 Jaehong Yoon , Saehoon Kim , Eunho Yang , Sung Ju Hwang

Deep learning methods - usually consisting of a class of deep neural networks (DNNs) trained by a stochastic gradient descent (SGD) optimization method - are nowadays omnipresent in data-driven learning problems as well as in scientific…

Optimization and Control · Mathematics 2025-01-13 Steffen Dereich , Arnulf Jentzen , Adrian Riekert

Adam is a widely used stochastic optimization method for deep learning applications. While practitioners prefer Adam because it requires less parameter tuning, its use is problematic from a theoretical point of view since it may not…

Machine Learning · Computer Science 2020-11-25 Mingrui Liu , Wei Zhang , Francesco Orabona , Tianbao Yang

With the capacity of continual learning, humans can continuously acquire knowledge throughout their lifespan. However, computational systems are not, in general, capable of learning tasks sequentially. This long-standing challenge for deep…

Machine Learning · Computer Science 2022-08-05 Qihan Yang , Fan Feng , Rosa Chan