Making scalable meta learning practical
Despite its flexibility to learn diverse inductive biases in machine learning programs, meta
learning (ie,\learning to learn) has long been recognized to suffer from poor scalability due …
learning (ie,\learning to learn) has long been recognized to suffer from poor scalability due …
Bidirectional learning for offline model-based biological sequence design
Offline model-based optimization aims to maximize a black-box objective function with a
static dataset of designs and their scores. In this paper, we focus on biological sequence …
static dataset of designs and their scores. In this paper, we focus on biological sequence …
Torchdeq: A library for deep equilibrium models
Deep Equilibrium (DEQ) Models, an emerging class of implicit models that maps inputs to
fixed points of neural networks, are of growing interest in the deep learning community …
fixed points of neural networks, are of growing interest in the deep learning community …
Nyström method for accurate and scalable implicit differentiation
The essential difficulty of gradient-based bilevel optimization using implicit differentiation is
to estimate the inverse Hessian vector product with respect to neural network parameters …
to estimate the inverse Hessian vector product with respect to neural network parameters …
Torchopt: An efficient library for differentiable optimization
Differentiable optimization algorithms often involve expensive computations of various meta-
gradients. To address this, we design and implement TorchOpt, a new PyTorch-based …
gradients. To address this, we design and implement TorchOpt, a new PyTorch-based …
Modality-agnostic self-supervised learning with meta-learned masked auto-encoder
Despite its practical importance across a wide range of modalities, recent advances in self-
supervised learning (SSL) have been primarily focused on a few well-curated domains, eg …
supervised learning (SSL) have been primarily focused on a few well-curated domains, eg …
Rethinking meta-learning from a learning lens
Meta-learning has emerged as a powerful approach for leveraging knowledge from previous
tasks to solve new tasks. The mainstream methods focus on training a well-generalized …
tasks to solve new tasks. The mainstream methods focus on training a well-generalized …
Efficient Meta label correction based on Meta Learning and bi-level optimization
The design of highly accurate deep learning architectures is related to different parameters
through different optimizations at different levels of the design. While the architectural design …
through different optimizations at different levels of the design. While the architectural design …
AutoLoRA: Automatically Tuning Matrix Ranks in Low-Rank Adaptation Based on Meta Learning
Large-scale pretraining followed by task-specific finetuning has achieved great success in
various NLP tasks. Since finetuning all parameters of large pretrained models poses …
various NLP tasks. Since finetuning all parameters of large pretrained models poses …
BiLoRA: A Bi-level Optimization Framework for Overfitting-Resilient Low-Rank Adaptation of Large Pre-trained Models
Low-rank adaptation (LoRA) is a popular method for fine-tuning large-scale pre-trained
models in downstream tasks by learning low-rank incremental matrices. Though LoRA and …
models in downstream tasks by learning low-rank incremental matrices. Though LoRA and …