University of Alberta（阿尔伯塔大学）；Google DeepMind（谷歌DeepMind）
Andrew Jacobsen, Matthew Schlegel, Cameron Linke, Thomas Degris, Adam White, Martha White
备注：
AAAI Conference on Artificial Intelligence 2019. v2: Correction to Baird's counterexample. A bug in the code lead to results being reported for AMSGrad in this experiment, when they were actually results for Adam
This paper investigates different vector step-size adaptation approaches for non-stationary online, continual prediction problems. Vanilla stochastic gradient descent can be considerably improved by scaling the update with a vector of appropriately chosen step-sizes. Many methods, including AdaGrad, RMSProp, and AMSGrad, keep statistics about the learning process to approximate a second order update---a vector approximation of the inverse Hessian. Another family of approaches use meta-gradient descent to adapt the step-size parameters to minimize prediction error. These meta-descent strategies are promising for non-stationary problems, but have not been as extensively explored as quasi-second order methods. We first derive a general, incremental meta-descent algorithm, called AdaGain, designed to be applicable to a much broader range of algorithms, including those with semi-gradient updates or even those with accelerations, such as RMSProp. We provide an empirical comparison of methods from both families. We conclude that methods from both families can perform well, but in non-stationary prediction problems the meta-descent methods exhibit advantages. Our method is particularly robust across several prediction problems, and is competitive with the state-of-the-art method on a large-scale, time-series prediction problem on real data from a mobile robot.
Aqemia；McGill University（麦吉尔大学）；Mila；RIKEN（理化学研究所）；The University of Tokyo（东京大学）
In Continual Learning settings, deep neural networks are prone to Catastrophic Forgetting. Orthogonal Gradient Descent was proposed to tackle the challenge. However, no theoretical guarantees have been proven yet. We present a theoretical framework to study Continual Learning algorithms in the Neural Tangent Kernel regime. This framework comprises closed form expression of the model through tasks and proxies for Transfer Learning, generalisation and tasks similarity. In this framework, we prove that OGD is robust to Catastrophic Forgetting then derive the first generalisation bound for SGD and…
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所）；Deepmind（深度思维）
The Backprop algorithm for learning in neural networks utilizes two mechanisms: first, stochastic gradient descent and second, initialization with small random weights, where the latter is essential to the effectiveness of the former. We show that in continual learning setups, Backprop performs well initially, but over time its performance degrades. Stochastic gradient descent alone is insufficient to learn continually; the initial randomness enables only initial learning but not continual learning. To the best of our knowledge, ours is the first result showing this degradation in Backprop's a…
Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks suffer from the problem of catastrophic forgetting; they forget how to solve previous tasks after being trained on a new task, despite having the essential capacity to solve both tasks if they were trained on both simultaneously. In this paper, we propose to address this issue from a parameter space perspective and study an approach to restrict the direction of t…
On the Theory of Continual Learning with Gradient Descent for Neural Networks
Department of Computer Science and Engineering, University of California, San Diego（加州大学圣地亚哥分校计算机科学与工程系）；Department of Computer Science and Engineering, IIT, Bombay（印度孟买理工学院计算机科学与工程系）；Halicioğlu Data Science Institute, University of California, San Diego（加州大学圣地亚哥分校Halicioğlu数据科学研究所）
The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual learning rely on stochastic gradient descent and its variants. However, these algorithms have to implement various strategies, such as memory buffers or replay, to overcome well-known shortcomings of stochastic gradient descent methods in terms of stability, greed, and short-term memory. To that end, we develop a biologically-inspired light weight neural network architecture that incorporates local learning and neuro…
In recent years, deep neural networks have found success in replicating human-level cognitive skills, yet they suffer from several major obstacles. One significant limitation is the inability to learn new tasks without forgetting previously learned tasks, a shortcoming known as catastrophic forgetting. In this research, we propose a simple method to overcome catastrophic forgetting and enable continual learning in neural networks. We draw inspiration from principles in neurology and physics to develop the concept of weight friction. Weight friction operates by a modification to the update rule…
In this report we consider the following problem: Given a trained model that is partially faulty, can we correct its behaviour without having to train the model from scratch? In other words, can we ``debug" neural networks similar to how we address bugs in our mathematical models and standard computer code. We base our approach on the hypothesis that debugging can be treated as a two-task continual learning problem. In particular, we employ a modified version of a continual learning algorithm called Orthogonal Gradient Descent (OGD) to demonstrate, via two simple experiments on the MNIST datas…
The purpose of this paper is to improve upon existing variants of gradient descent by solving two problems: (1) removing (or reducing) the plateau that occurs while minimizing the cost function, (2) continually adjusting the learning rate to an "ideal" value. The approach taken is to approximately solve for the learning rate as a function of a trust metric. When this technique is hybridized with momentum, it creates an especially effective gradient descent variant, called NeogradM. It is shown to outperform Adam on several test problems, and can easily reach cost function values that are small…
From Continual Learning to SGD and Back: Better Rates for Continual Linear Models
Meta；Technion（技术ion学院）；Department of Computer Science（计算机科学系）；Tel Aviv University（特拉维夫大学）；Blavatnik School of Computer Science and AI（Blavatnik计算机科学与人工智能学院）；Google Research（谷歌研究）；Department of Electrical and Computing Engineering（电气与计算工程系）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）
Norwegian University of Science and Technology（挪威科技大学）
In this paper, we generalize the problem of single-index model to the context of continual learning in which a learner is challenged with a sequence of tasks one by one and the dataset of each task is revealed in an online fashion. We propose a randomized strategy that is able to learn a common single-index (meta-parameter) for all tasks and a specific link function for each task. The common single-index allows to transfer the information gained from the previous tasks to a new one. We provide a rigorous theoretical analysis of our proposed strategy by proving some regret bounds under differen…
Learning from data sequentially arriving, possibly in a non i.i.d. way, with changing task distribution over time is called continual learning. Much of the work thus far in continual learning focuses on supervised learning and some recent works on unsupervised learning. In many domains, each task contains a mix of labelled (typically very few) and unlabelled (typically plenty) training examples, which necessitates a semi-supervised learning approach. To address this in a continual learning setting, we propose a framework for semi-supervised continual learning called Meta-Consolidation for Cont…
University of Edinburgh（爱丁堡大学）；University of Cambridge（剑桥大学）
It is difficult to continually update private machine learning models with new data while maintaining privacy. Data incur increasing privacy loss -- as measured by differential privacy -- when they are used in repeated computations. In this paper, we describe regularized empirical risk minimization algorithms that continually release models for a recent window of data. One version of the algorithm uses the entire data history to improve the model for the recent window. The second version uses a sliding window of constant size to improve the model, ensuring more relevant models in case of evolv…
University of Vermont（佛蒙特大学）；Uber AI Labs（优步人工智能实验室）；OpenAI（开放人工智能研究中心）
Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine learning models to catastrophically forget, yet virtually all such work involves manually-designed solutions to the problem. We instead advocate meta-learning a solution to catastrophic forgetting, allowing AI to learn to continually learn. Inspired by neuromodulatory processes in the brain, we propose A Neuromodulated Meta-Learning Algorithm (ANML). It differ…
Optimal Rates in Continual Linear Regression via Increasing Regularization
Department of Computer Science, Technion（技术学院计算机科学系）；Blavatnik School of Computer Science and AI, Tel Aviv University（特拉维夫大学Blavatnik计算机科学与人工智能学院）；Department of Electrical and Computer Engineering, Technion（技术学院电气与计算机工程系）
Tsinghua-Berkeley Shenzhen Institute（清华-伯克利深圳学院）；Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院）；Tsinghua University（清华大学）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of California, Berkeley（加州大学伯克利分校）
Models trained with offline data often suffer from continual distribution shifts and expensive labeling in changing environments. This calls for a new online learning paradigm where the learner can continually adapt to changing environments with limited labels. In this paper, we propose a new online setting -- Online Active Continual Adaptation, where the learner aims to continually adapt to changing distributions using both unlabeled samples and active queries of limited labels. To this end, we propose Online Self-Adaptive Mirror Descent (OSAMD), which adopts an online teacher-student structu…
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）
In computational reinforcement learning, a growing body of work seeks to construct an agent's perception of the world through predictions of future sensations; predictions about environment observations are used as additional input features to enable better goal-directed decision-making. An open challenge in this line of work is determining from the infinitely many predictions that the agent could possibly make which predictions might best support decision-making. This challenge is especially apparent in continual learning problems where a single stream of experience is available to a singular…
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 rapid online adaptation. The goal in this paper is to develop a method for continual online learning from an incoming stream of data, using deep neural network models. We formulate an online learning procedure that uses stochastic gradient descent to update model parameters, and an …
University of Pennsylvania（宾夕法尼亚大学）；DeepMind（深度思维）
Continual learning is the problem of learning new tasks or knowledge while protecting old knowledge and ideally generalizing from old experience to learn new tasks faster. Neural networks trained by stochastic gradient descent often degrade on old tasks when trained successively on new tasks with different data distributions. This phenomenon, referred to as catastrophic forgetting, is considered a major hurdle to learning with non-stationary data or sequences of new tasks, and prevents networks from continually accumulating knowledge and skills. We examine this issue in the context of reinforc…
Wellcome Centre for Integrative Neuroimaging（惠康综合神经影像中心）；University of Oxford（牛津大学）
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, the ability of artificial neural networks (ANNs) to learn across a range of tasks and domains, combining and re-using learned representations where required, is a clear goal of artificial intelligence. This capacity, widely described as continual learning, has become a prolific subfield of research in machine learning. Despite the numerous successes of deep le…
Representations are fundamental to artificial intelligence. The performance of a learning system depends on the type of representation used for representing the data. Typically, these representations are hand-engineered using domain knowledge. More recently, the trend is to learn these representations through stochastic gradient descent in multi-layer neural networks, which is called backprop. Learning the representations directly from the incoming data stream reduces the human labour involved in designing a learning system. More importantly, this allows in scaling of a learning system for dif…
University of Edinburgh（爱丁堡大学）；KAIST（韩国科学技术院）；Samsung AI Research, Cambridge（三星剑桥人工智能研究院）
Optimisers are an essential component for training machine learning models, and their design influences learning speed and generalisation. Several studies have attempted to learn more effective gradient-descent optimisers via solving a bi-level optimisation problem where generalisation error is minimised with respect to optimiser parameters. However, most existing optimiser learning methods are intuitively motivated, without clear theoretical support. We take a different perspective starting from mirror descent rather than gradient descent, and meta-learning the corresponding Bregman divergenc…
The University of Manchester（曼彻斯特大学）；The Alan Turing Institute（艾伦·图灵研究所）；DeepMind（深度思维）
Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works have approached this issue either by attempting to train a neural network that directly produces updates or by attempting to learn better initialisations or scaling factors for a gradient-based update rule. Both of these approaches pose challenges. On one hand, directly producing an update forgoes a useful inductive bias and can easily lead to non-converging behaviour. On the other hand, approaches that try to contr…
We propose \textit{Meta-Regularization}, a novel approach for the adaptive choice of the learning rate in first-order gradient descent methods. Our approach modifies the objective function by adding a regularization term on the learning rate, and casts the joint updating process of parameters and learning rates into a maxmin problem. Given any regularization term, our approach facilitates the generation of practical algorithms. When \textit{Meta-Regularization} takes the $φ$-divergence as a regularizer, the resulting algorithms exhibit comparable theoretical convergence performance with other …
Massachusetts Institute of Technology（麻省理工学院）；California Institute of Technology（加州理工学院）
Despite perfectly interpolating the training data, deep neural networks (DNNs) can often generalize fairly well, in part due to the "implicit regularization" induced by the learning algorithm. Nonetheless, various forms of regularization, such as "explicit regularization" (via weight decay), are often used to avoid overfitting, especially when the data is corrupted. There are several challenges with explicit regularization, most notably unclear convergence properties. Inspired by convergence properties of stochastic mirror descent (SMD) algorithms, we propose a new method for training DNNs wit…
Learning to learn is a powerful paradigm for enabling models to learn from data more effectively and efficiently. A popular approach to meta-learning is to train a recurrent model to read in a training dataset as input and output the parameters of a learned model, or output predictions for new test inputs. Alternatively, a more recent approach to meta-learning aims to acquire deep representations that can be effectively fine-tuned, via standard gradient descent, to new tasks. In this paper, we consider the meta-learning problem from the perspective of universality, formalizing the notion of le…
Amirkabir University of Technology（阿米尔卡比尔理工大学）；Shiraz University（设拉子大学）
Gradient Descent (GD) approximators often fail in the solution space with multiple scales of convexities, i.e., in subspace learning and neural network scenarios. To handle that, one solution is to run GD multiple times from different randomized initial states and select the best solution over all experiments. However, this idea is proved impractical in plenty of cases. Even Swarm-based optimizers like Particle Swarm Optimization (PSO) or Imperialistic Competitive Algorithm (ICA), as commonly used GD initializers, have failed to find optimal solutions in some applications. In this paper, Swarm…
The performance of a syntax-guided synthesis algorithm is highly dependent on the provision of a good syntactic template, or grammar. Provision of such a template is often left to the user to do manually, though in the absence of such a grammar, state-of-the-art solvers will provide their own default grammar, which is dependent on the signature of the target program to be sythesized. In this work, we speculate this default grammar could be improved upon substantially. We build sets of rules, or metagrammars, for constructing grammars, and perform a gradient descent over these metagrammars aimi…
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）
In computational reinforcement learning, a growing body of work seeks to express an agent's model of the world through predictions about future sensations. In this manuscript we focus on predictions expressed as General Value Functions: temporally extended estimates of the accumulation of a future signal. One challenge is determining from the infinitely many predictions that the agent could possibly make which might support decision-making. In this work, we contribute a meta-gradient descent method by which an agent can directly specify what predictions it learns, independent of designer instr…
Peter Grünberg Institute – Neuromorphic Software Ecosystems（彼得·格伦贝格研究所——神经形态软件生态系统）；Forschungszentrum Jülich（于利希研究中心）；RWTH Aachen（亚琛工业大学）；UC Irvine（加州大学欧文分校）
Adaptive "life-long" learning at the edge and during online task performance is an aspirational goal of AI research. Neuromorphic hardware implementing Spiking Neural Networks (SNNs) are particularly attractive in this regard, as their real-time, event-based, local computing paradigm makes them suitable for edge implementations and fast learning. However, the long and iterative learning that characterizes state-of-the-art SNN training is incompatible with the physical nature and real-time operation of neuromorphic hardware. Bi-level learning, such as meta-learning is increasingly used in deep …
We propose firefly neural architecture descent, a general framework for progressively and dynamically growing neural networks to jointly optimize the networks' parameters and architectures. Our method works in a steepest descent fashion, which iteratively finds the best network within a functional neighborhood of the original network that includes a diverse set of candidate network structures. By using Taylor approximation, the optimal network structure in the neighborhood can be found with a greedy selection procedure. We show that firefly descent can flexibly grow networks both wider and dee…
The continual learning problem involves training models with limited capacity to perform well on a set of an unknown number of sequentially arriving tasks. While meta-learning shows great potential for reducing interference between old and new tasks, the current training procedures tend to be either slow or offline, and sensitive to many hyper-parameters. In this work, we propose Look-ahead MAML (La-MAML), a fast optimisation-based meta-learning algorithm for online-continual learning, aided by a small episodic memory. Our proposed modulation of per-parameter learning rates in our meta-learnin…
Duke University（杜克大学）；UC Berkeley（加州大学伯克利分校）；Princeton University（普林斯顿大学）
Learning-to-learn or meta-learning leverages data-driven inductive bias to increase the efficiency of learning on a novel task. This approach encounters difficulty when transfer is not advantageous, for instance, when tasks are considerably dissimilar or change over time. We use the connection between gradient-based meta-learning and hierarchical Bayes to propose a Dirichlet process mixture of hierarchical Bayesian models over the parameters of an arbitrary parametric model such as a neural network. In contrast to consolidating inductive biases into a single set of hyperparameters, our approac…
The University of Queensland（昆士兰大学）；Harbin Institute of Technology（哈尔滨工业大学）；Pengcheng Laboratory（鹏城实验室）；University of Electronic Science and Technology of China（电子科技大学）
Meta-learning for few-shot learning allows a machine to leverage previously acquired knowledge as a prior, thus improving the performance on novel tasks with only small amounts of data. However, most mainstream models suffer from catastrophic forgetting and insufficient robustness issues, thereby failing to fully retain or exploit long-term knowledge while being prone to cause severe error accumulation. In this paper, we propose a novel Continual Meta-Learning approach with Bayesian Graph Neural Networks (CML-BGNN) that mathematically formulates meta-learning as continual learning of a sequenc…
Although continual learning and anomaly detection have separately been well-studied in previous works, their intersection remains rather unexplored. The present work addresses a learning scenario where a model has to incrementally learn a sequence of anomaly detection tasks, i.e. tasks from which only examples from the normal (majority) class are available for training. We define this novel learning problem of continual anomaly detection (CAD) and formulate it as a meta-learning problem. Moreover, we propose A Rapid Continual Anomaly Detector (ARCADe), an approach to train neural networks to b…
A continual learning agent should be able to build on top of existing knowledge to learn on new data quickly while minimizing forgetting. Current intelligent systems based on neural network function approximators arguably do the opposite---they are highly prone to forgetting and rarely trained to facilitate future learning. One reason for this poor behavior is that they learn from a representation that is not explicitly trained for these two goals. In this paper, we propose OML, an objective that directly minimizes catastrophic interference by learning representations that accelerate future le…
Mathematics and Computer Science Division（数学与计算机科学部）；Leadership Computing Facility（领导力计算设施）；Argonne National Laboratory（阿贡国家实验室）
Meta continual learning algorithms seek to train a model when faced with similar tasks observed in a sequential manner. Despite promising methodological advancements, there is a lack of theoretical frameworks that enable analysis of learning challenges such as generalization and catastrophic forgetting. To that end, we develop a new theoretical approach for meta continual learning~(MCL) where we mathematically model the learning dynamics using dynamic programming, and we establish conditions of optimality for the MCL problem. Moreover, using the theoretical framework, we derive a new dynamic-p…
ElementAI（ElementAI公司）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）；Facebook AI Research（脸书人工智能研究院）；McGill University（麦吉尔大学）；HEC Montréal（蒙特利尔高等商学院）
Continual learning studies agents that learn from streams of tasks without forgetting previous ones while adapting to new ones. Two recent continual-learning scenarios have opened new avenues of research. In meta-continual learning, the model is pre-trained to minimize catastrophic forgetting of previous tasks. In continual-meta learning, the aim is to train agents for faster remembering of previous tasks through adaptation. In their original formulations, both methods have limitations. We stand on their shoulders to propose a more general scenario, OSAKA, where an agent must quickly solve new…
Continual learning aims to alleviate catastrophic forgetting when handling consecutive tasks under non-stationary distributions. Gradient-based meta-learning algorithms have shown the capability to implicitly solve the transfer-interference trade-off problem between different examples. However, they still suffer from the catastrophic forgetting problem in the setting of continual learning, since the past data of previous tasks are no longer available. In this work, we propose a novel efficient meta-learning algorithm for solving the online continual learning problem, where the regularization t…
University of Southern California（南加州大学）；Intel Labs（英特尔实验室）
Continual learning systems will interact with humans, with each other, and with the physical world through time -- and continue to learn and adapt as they do. An important open problem for continual learning is a large-scale benchmark that enables realistic evaluation of algorithms. In this paper, we study a natural setting for continual learning on a massive scale. We introduce the problem of personalized online language learning (POLL), which involves fitting personalized language models to a population of users that evolves over time. To facilitate research on POLL, we collect massive datas…
While neural networks are powerful function approximators, they suffer from catastrophic forgetting when the data distribution is not stationary. One particular formalism that studies learning under non-stationary distribution is provided by continual learning, where the non-stationarity is imposed by a sequence of distinct tasks. Most methods in this space assume, however, the knowledge of task boundaries, and focus on alleviating catastrophic forgetting. In this work, we depart from this view and move the focus towards faster remembering -- i.e measuring how quickly the network recovers perf…
Sequential learning of tasks using gradient descent leads to an unremitting decline in the accuracy of tasks for which training data is no longer available, termed catastrophic forgetting. Generative models have been explored as a means to approximate the distribution of old tasks and bypass storage of real data. Here we propose a cumulative closed-loop memory replay GAN (CloGAN) provided with external regularization by a small memory unit selected for maximum sample diversity. We evaluate incremental class learning using a notoriously hard paradigm, single-headed learning, in which each task …
