A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
La-MAML improves fast online continual learning with a look-ahead approach.
New method uses dynamic programming for meta continual learning.
Paper introduces a meta-critic for accelerating off-policy actor-critic learning.
Meta-learning is a promising strategy for learning to efficiently learn within new tasks, using data gathered from a distribution of tasks. However, the meta-learning literature thus far has focused on the task segmented setting, where at train-time, offline data is assumed to be split according to the underlying task,…
The paper proposes a learning algorithm that improves adaptability and generalization.
Novel Bayesian meta-reinforcement learning framework improves traffic signal control robustness.
This paper surveys meta-learning, online, and continual learning.
Meta-continual learning improves few-shot learning performance.
ARCADe detects anomalies in a sequence of tasks with limited data.
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 m…
Faster ZSL with continual learning and self-gating.
Proposes a framework for semi-supervised continual learning from sequentially arriving data.
Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past traject…
We derive the ODE of MAML and propose a new BI-MAML algorithm.
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 retai…
In this paper we propose to solve an important problem in recommendation -- user cold start, based on meta leaning method. Previous meta learning approaches finetune all parameters for each new user, which is both computing and storage expensive. In contrast, we divide model parameters into fixed and adaptive parts and…
M3PO improves model-based meta-RL with theoretical guarantees.
Learning to optimize has emerged as a powerful framework for various optimization and machine learning tasks. Current such "meta-optimizers" often learn in the space of continuous optimization algorithms that are point-based and uncertainty-unaware. To overcome the limitations, we propose a meta-optimizer that learns i…
Meta-learning, or learning to learn, is the science of systematically observing how different machine learning approaches perform on a wide range of learning tasks, and then learning from this experience, or meta-data, to learn new tasks much faster than otherwise possible. Not only does this dramatically speed up and …
Paper tackles continual learning with single-index models, proving regret bounds.
MAIN network learns attributes without unseen class attributes for faster, more adaptable ZSL.
Neural networks have been successfully applied in applications with a large amount of labeled data. However, the task of rapid generalization on new concepts with small training data while preserving performances on previously learned ones still presents a significant challenge to neural network models. In this work, w…
Evolutionary Strategies optimize hyper-parameters for off-policy learning.
Meta-learning for discrete tasks using submodular optimization.
A central capability of intelligent systems is the ability to continuously build upon previous experiences to speed up and enhance learning of new tasks. Two distinct research paradigms have studied this question. Meta-learning views this problem as learning a prior over model parameters that is amenable for fast adapt…
Reinforcement learning (RL) algorithms have demonstrated promising results on complex tasks, yet often require impractical numbers of samples since they learn from scratch. Meta-RL aims to address this challenge by leveraging experience from previous tasks so as to more quickly solve new tasks. However, in practice, th…
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 rap…
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 dis…
In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks. However, a critical challenge in meta-learning is task uncertainty and heterogeneity, which can not be handled via globally sharing knowledge among tasks. In this paper, based on gradient-based meta-learning,…
New method for online meta-learning reduces dynamic regret in changing environments.
Meta-learning is a promising method to achieve efficient training method towards deep neural net and has been attracting increases interests in recent years. But most of the current methods are still not capable to train complex neuron net model with long-time training process. In this paper, a novel second-order meta-…
Sparse Meta Networks adapt deep neural networks incrementally for fast learning.
MAT combines meta-learning and adversarial training to defend against universal patches.
The online meta-learning framework is designed for the continual lifelong learning setting. It bridges two fields: meta-learning which tries to extract prior knowledge from past tasks for fast learning of future tasks, and online-learning which deals with the sequential setting where problems are revealed one by one. I…
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 me…
Empirical study shows consistent meta-RL algorithms adapt to OOD tasks.
Meta-learning approach improves object detection on new classes.
FLAP adapts policies quickly to new tasks using shared linear representations.
Lack of performance when it comes to continual learning over non-stationary distributions of data remains a major challenge in scaling neural network learning to more human realistic settings. In this work we propose a new conceptualization of the continual learning problem in terms of a temporally symmetric trade-off …
Meta-learning approach prevents forgetting across tasks.
Meta Optimal Transport learns from past problems to solve similar OT problems faster.
Algorithm learns new tasks efficiently from past experience.
A new method improves EEG classification across subjects efficiently.
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 AMSGra…
Meta-learning neural networks for better clustering representations.
Bayesian approach helps update deep models without forgetting past data.
AdMRL improves meta-reinforcement learning by minimizing worst-case sub-optimality gap.