Related papers: Meta-Learning with a Geometry-Adaptive Preconditio…
Meta-learning has arisen as a successful method for improving training performance by training over many similar tasks, especially with deep neural networks (DNNs). However, the theoretical understanding of when and why overparameterized…
With the growing attention on learning-to-learn new tasks using only a few examples, meta-learning has been widely used in numerous problems such as few-shot classification, reinforcement learning, and domain generalization. However,…
The conjugate gradient solver (CG) is a prevalent method for solving symmetric and positive definite linear systems Ax=b, where effective preconditioners are crucial for fast convergence. Traditional preconditioners rely on prescribed…
Large pretrained language models have shown surprising in-context learning (ICL) ability. With a few demonstration input-label pairs, they can predict the label for an unseen input without parameter updates. Despite the great success in…
Meta-learning, or learning to learn, is a technique that can help to overcome resource scarcity in cross-lingual NLP problems, by enabling fast adaptation to new tasks. We apply model-agnostic meta-learning (MAML) to the task of…
Fully automating machine learning pipelines is one of the key challenges of current artificial intelligence research, since practical machine learning often requires costly and time-consuming human-powered processes such as model design,…
A broad class of unsupervised deep learning methods such as Generative Adversarial Networks (GANs) involve training of overparameterized models where the number of parameters of the model exceeds a certain threshold. A large body of work in…
Model-agnostic meta-learning (MAML) has been recently put forth as a strategy to learn resource-poor languages in a sample-efficient fashion. Nevertheless, the properties of these languages are often not well represented by those available…
We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential…
Widely used traditional supervised deep learning methods require a large number of training samples but often fail to generalize on unseen datasets. Therefore, a more general application of any trained model is quite limited for medical…
Machine-learning interatomic potentials (MLIPs) such as neuroevolution potentials (NEP) combine quantum-mechanical accuracy with computational efficiency significantly accelerate atomistic dynamic simulations. Trained by derivative-free…
Deep neural networks can yield good performance on various tasks but often require large amounts of data to train them. Meta-learning received considerable attention as one approach to improve the generalization of these networks from a…
Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet…
The representations of the Earth's surface vary from one geographic region to another. For instance, the appearance of urban areas differs between continents, and seasonality influences the appearance of vegetation. To capture the diversity…
We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-overfitting, easier to parallelise, and more interpretable. CAVIA partitions the model parameters into two parts: context parameters that serve as…
Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as a distinct semantic entity and GAP as a combination of…
We present a novel Balanced Incremental Model Agnostic Meta Learning system (BI-MAML) for learning multiple tasks. Our method implements a meta-update rule to incrementally adapt its model to new tasks without forgetting old tasks. Such a…
At the heart of the standard deep learning training loop is a greedy gradient step minimizing a given loss. We propose to add a second step to maximize training generalization. To do this, we optimize the loss of the next training step.…
Linear attention methods offer a compelling alternative to softmax attention due to their efficiency in recurrent decoding. Recent research has focused on enhancing standard linear attention by incorporating gating while retaining its…
The remarkable capability of Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with…