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.
M3PO improves model-based meta-RL with theoretical guarantees.
Meta-learning adapts models for unseen tasks across AI, robotics, and NLP.
Meta-learning overfits both model and base learner; meta-augmentation helps.
Bayesian MAML outperforms MAML in meta learning tasks with theoretical guarantees.
Meta learning works well with overparameterized models, a phenomenon called 'benign overfitting'.
Meta-learning balances task-specific modeling and optimization complexity.
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnostic meta-learning method. The proposed method combines scalable gradient-based meta-learning with non…
Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks,where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph only considers the complex structural information, but i…
A new meta-analysis model detects and accommodates outliers.
Paper tackles offline meta-reinforcement learning with a new algorithm.
Meta-learning algorithms produce feature extractors which achieve state-of-the-art performance on few-shot classification. While the literature is rich with meta-learning methods, little is known about why the resulting feature extractors perform so well. We develop a better understanding of the underlying mechanics of…
Existing meta-learning based few-shot learning (FSL) methods typically adopt an episodic training strategy whereby each episode contains a meta-task. Across episodes, these tasks are sampled randomly and their relationships are ignored. In this paper, we argue that the inter-meta-task relationships should be exploited …
When fitting Bayesian machine learning models on scarce data, the main challenge is to obtain suitable prior knowledge and encode it into the model. Recent advances in meta-learning offer powerful methods for extracting such prior knowledge from data acquired in related tasks. When it comes to meta-learning in Gaussian…
Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large dataset and a testing phase, where the meta-learner leverages its learnt internal rep…
A new method generates meta-tasks using generative models for unsupervised learning.
Meta-learning algorithm improves AI efficiency by teaching itself.
The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better capture complex task distributions and improve performance. However, many existing c…
Meta-learning is a field that aims at discovering how different machine learning algorithms perform on a wide range of predictive tasks. Such knowledge speeds up the hyperparameter tuning or feature engineering. With the use of surrogate models various aspects of the predictive task such as meta-features, landmarker mo…
Transformers learn to solve various tasks without explicit design.
Meta-learning approaches have been proposed to tackle the few-shot learning problem.Typically, a meta-learner is trained on a variety of tasks in the hopes of being generalizable to new tasks. However, the generalizability on new tasks of a meta-learner could be fragile when it is over-trained on existing tasks during …
ScaML-GP efficiently learns from few meta-tasks using Gaussian processes.
BOML unifies meta-learning methods into a common bilevel optimization framework.
Meta-learning algorithms prepare quantum Gibbs states efficiently for NISQ devices.
Meta-SAGE improves deep RL scalability for CO tasks by adapting pre-trained models to larger-scale problems.
Several multi-target regression methods were devel-oped in the last years aiming at improving predictive performanceby exploring inter-target correlation within the problem. However, none of these methods outperforms the others for all problems. This motivates the development of automatic approachesto recommend the mos…
Meta-learning has received a tremendous recent attention as a possible approach for mimicking human intelligence, i.e., acquiring new knowledge and skills with little or even no demonstration. Most of the existing meta-learning methods are proposed to tackle few-shot learning problems such as image and text, in rather …
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…
Meta Omnium benchmarks few-shot learning across diverse vision tasks.
A tensor model for meta-learning adapts to task-specific features.
Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model applicable to the tasks with new structures, it is required to collect new training d…
Gradient-based meta-learners such as Model-Agnostic Meta-Learning (MAML) have shown strong few-shot performance in supervised and reinforcement learning settings. However, specifically in the case of meta-reinforcement learning (meta-RL), we can show that gradient-based meta-learners are sensitive to task distributions…
Meta-learning improves with explicit modeling of task covariate distributions.
MSLG generates soft labels to improve DNN performance on noisy datasets.
Paper proposes Meta Label Learning to infer global labels for robust few-shot models.
A new method improves few-shot image classification by updating top layers.
Meta-learning helps models learn quickly from few samples.
Meta-learning bound uses conditional mutual information.
The capacity of meta-learning algorithms to quickly adapt to a variety of tasks, including ones they did not experience during meta-training, has been a key factor in the recent success of these methods on few-shot learning problems. This particular advantage of using meta-learning over standard supervised or reinforce…
Unified framework improves meta-learning generalization bounds.
Meta-learning framework uses task similarity through nonparametric kernel regression.
In this work we study generalization of neural networks in gradient-based meta-learning by analyzing various properties of the objective landscapes. We experimentally demonstrate that as meta-training progresses, the meta-test solutions, obtained after adapting the meta-train solution of the model, to new tasks via few…
Few-shot classification is the task of predicting the category of an example from a set of few labeled examples. The number of labeled examples per category is called the number of shots (or shot number). Recent works tackle this task through meta-learning, where a meta-learner extracts information from observed tasks …
VMGP extends Gaussian processes for Bayesian meta-learning, improving uncertainty prediction.
ST-MAML tackles task ambiguity in meta-learning by encoding tasks with stochastic representations.
Meta-learning improves Gaussian process uncertainty estimation.
A new meta-learning framework that assigns weights to source tasks based on target samples.
Meta-learning enables a model to learn from very limited data to undertake a new task. In this paper, we study the general meta-learning with adversarial samples. We present a meta-learning algorithm, ADML (ADversarial Meta-Learner), which leverages clean and adversarial samples to optimize the initialization of a lear…
New approach avoids meta-amortization error in few-shot learning.