English
Related papers

Related papers: Careful with that Scalpel: Improving Gradient Surg…

200 papers

Bilevel optimization is a powerful tool for many machine learning problems, such as hyperparameter optimization and meta-learning. Estimating hypergradients (also known as implicit gradients) is crucial for developing gradient-based methods…

Optimization and Control · Mathematics 2025-05-06 Youran Dong , Junfeng Yang , Wei Yao , Jin Zhang

Few-shot meta-learning presents a challenge for gradient descent optimization due to the limited number of training samples per task. To address this issue, we propose an episodic memory optimization for meta-learning, we call EMO, which is…

Machine Learning · Computer Science 2023-06-28 Yingjun Du , Jiayi Shen , Xiantong Zhen , Cees G. M. Snoek

Additive parameter updates, as used in gradient descent and its adaptive extensions, underpin most modern machine-learning optimization. Yet, such additive schemes often demand numerous iterations and intricate learning-rate schedules to…

Machine Learning · Computer Science 2026-03-25 Han Kim , Hyungjoon Soh , Vipul Periwal , Junghyo Jo

We consider optimization problems in which the objective requires an inner loop with many steps or is the limit of a sequence of increasingly costly approximations. Meta-learning, training recurrent neural networks, and optimization of the…

Machine Learning · Computer Science 2019-05-20 Alex Beatson , Ryan P. Adams

Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental studies have demonstrated a fairly special behavior in the…

Machine Learning · Computer Science 2023-06-06 Amirhossein Reisizadeh , Haochuan Li , Subhro Das , Ali Jadbabaie

To accelerate learning process with few samples, meta-learning resorts to prior knowledge from previous tasks. However, the inconsistent task distribution and heterogeneity is hard to be handled through a global sharing model…

Machine Learning · Computer Science 2022-06-22 Geng Li , Boyuan Ren , Hongzhi Wang

Momentum based optimizers are central to a wide range of machine learning applications. These typically rely on an Exponential Moving Average (EMA) of gradients, which decays exponentially the present contribution of older gradients. This…

Machine Learning · Computer Science 2024-10-01 Matteo Pagliardini , Pierre Ablin , David Grangier

We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks. This problem has broad applications in NLP, such as targeted instruction tuning and data selection in…

Computation and Language · Computer Science 2025-06-03 Dongyue Li , Ziniu Zhang , Lu Wang , Hongyang R. Zhang

The multi-task learning ($MTL$) paradigm aims to simultaneously learn multiple tasks within a single model capturing higher-level, more general hidden patterns that are shared by the tasks. In deep learning, a significant challenge in the…

Machine Learning · Computer Science 2025-06-09 Thomas Borsani , Andrea Rosani , Giuseppe Nicosia , Giuseppe Di Fatta

Mixture-of-Experts (MoE) models enable efficient scaling of large language models (LLMs) by activating only a subset of experts per input. However, we observe that the commonly used auxiliary load balancing loss often leads to expert…

Computation and Language · Computer Science 2026-01-27 Hongcan Guo , Haolang Lu , Guoshun Nan , Bolun Chu , Jialin Zhuang , Yuan Yang , Wenhao Che , Xinye Cao , Sicong Leng , Qimei Cui , Xudong Jiang

This paper reveals that a common and central role, played in many error bound (EB) conditions and a variety of gradient-type methods, is a residual measure operator. On one hand, by linking this operator with other optimality measures, we…

Optimization and Control · Mathematics 2018-05-17 Hui Zhang

This paper addresses supervised deep metric learning for open-set image retrieval, focusing on three key aspects: the loss function, mixup regularization, and model initialization. In deep metric learning, optimizing the retrieval…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Yash Patel , Giorgos Tolias , Jiri Matas

Data mixing--the strategic reweighting of training domains--is a critical component in training robust machine learning models. This problem is naturally formulated as a bilevel optimization task, where the outer loop optimizes domain…

Machine Learning · Computer Science 2026-02-24 Rudrajit Das , Neel Patel , Meisam Razaviyayn , Vahab Mirrokni

In recent years, a variety of gradient-based methods have been developed to solve Bi-Level Optimization (BLO) problems in machine learning and computer vision areas. However, the theoretical correctness and practical effectiveness of these…

Machine Learning · Computer Science 2022-01-04 Risheng Liu , Pan Mu , Xiaoming Yuan , Shangzhi Zeng , Jin Zhang

State-of-the-art training algorithms for deep learning models are based on stochastic gradient descent (SGD). Recently, many variations have been explored: perturbing parameters for better accuracy (such as in Extragradient), limiting SGD…

Machine Learning · Computer Science 2022-03-23 Amirkeivan Mohtashami , Martin Jaggi , Sebastian U. Stich

The goal of few-shot learning is to generalize and achieve high performance on new unseen learning tasks, where each task has only a limited number of examples available. Gradient-based meta-learning attempts to address this challenging…

Machine Learning · Computer Science 2024-06-13 Christian Raymond , Qi Chen , Bing Xue , Mengjie Zhang

The recently introduced Gradient Methods with Memory use a subset of the past oracle information to create an accurate model of the objective function that enables them to surpass the Gradient Method in practical performance. The model…

Optimization and Control · Mathematics 2024-01-30 Mihai I. Florea

Low-Rank Adaptation (LoRA) improves downstream performance by restricting task updates to a low-rank parameter subspace, yet how this limited capacity is allocated within a trained adapter remains unclear. Through a geometric and empirical…

Machine Learning · Computer Science 2026-03-05 Zailong Tian , Yanzhe Chen , Zhuoheng Han , Lizi Liao

The current state-of-the-art for few-shot cross-lingual transfer learning first trains on abundant labeled data in the source language and then fine-tunes with a few examples on the target language, termed target-adapting. Though this has…

Computation and Language · Computer Science 2022-05-02 Haoran Xu , Kenton Murray

The simplicity of gradient descent (GD) made it the default method for training ever-deeper and complex neural networks. Both loss functions and architectures are often explicitly tuned to be amenable to this basic local optimization. In…

Machine Learning · Computer Science 2019-04-30 Dmitrii Marin , Meng Tang , Ismail Ben Ayed , Yuri Boykov