English
Related papers

Related papers: Personalizing black-box models for nonparametric r…

200 papers

Prompts for pre-trained language models (PLMs) have shown remarkable performance by bridging the gap between pre-training tasks and various downstream tasks. Among these methods, prompt tuning, which freezes PLMs and only tunes soft…

Computation and Language · Computer Science 2022-03-15 Yuxian Gu , Xu Han , Zhiyuan Liu , Minlie Huang

While advances in pre-training have led to dramatic improvements in few-shot learning of NLP tasks, there is limited understanding of what drives successful few-shot adaptation in datasets. In particular, given a new dataset and a…

Computation and Language · Computer Science 2022-11-17 Xinran Zhao , Shikhar Murty , Christopher D. Manning

Recent development of large-scale pre-trained language models (PLM) have significantly improved the capability of models in various NLP tasks, in terms of performance after task-specific fine-tuning and zero-shot / few-shot learning.…

Computation and Language · Computer Science 2022-04-21 Chenguang Zhu , Michael Zeng

Deep neural networks have been able to outperform humans in some cases like image recognition and image classification. However, with the emergence of various novel categories, the ability to continuously widen the learning capability of…

Computer Vision and Pattern Recognition · Computer Science 2020-07-31 Nihar Bendre , Hugo Terashima Marín , Peyman Najafirad

Black-box tuning is an emerging paradigm for adapting large language models (LLMs) to better achieve desired behaviors, particularly when direct access to model parameters is unavailable. Current strategies, however, often present a dilemma…

Artificial Intelligence · Computer Science 2025-12-17 Zhikang Xie , Weilin Wan , Peizhu Gong , Weizhong Zhang , Cheng Jin

In training neural networks, it is common practice to use partial gradients computed over batches, mostly very small subsets of the training set. This approach is motivated by the argument that such a partial gradient is close to the true…

Machine Learning · Computer Science 2024-11-25 Jan Spörer , Bernhard Bermeitinger , Tomas Hrycej , Niklas Limacher , Siegfried Handschuh

There has been significant recent progress in training differentially private (DP) models which achieve accuracy that approaches the best non-private models. These DP models are typically pretrained on large public datasets and then…

With the deluge of digitized information in the Big Data era, massive datasets are becoming increasingly available for learning predictive models. However, in many practical situations, the poor control of the data acquisition processes may…

Machine Learning · Statistics 2022-11-02 Stephan Clémençon , Pierre Laforgue

Transfer learning has emerged as a powerful technique for improving the performance of machine learning models on new domains where labeled training data may be scarce. In this approach a model trained for a source task, where plenty of…

Machine Learning · Computer Science 2020-06-19 Seyed Mohammadreza Mousavi Kalan , Zalan Fabian , A. Salman Avestimehr , Mahdi Soltanolkotabi

In recent years, few-shot learning problems have received a lot of attention. While methods in most previous works were trained and tested on datasets in one single domain, cross-domain few-shot learning is a brand-new branch of few-shot…

Machine Learning · Computer Science 2024-02-07 Jia-Fong Yeh , Hsin-Ying Lee , Bing-Chen Tsai , Yi-Rong Chen , Ping-Chia Huang , Winston H. Hsu

In this paper, we present a novel nonlinear programming-based approach to fine-tune pre-trained neural networks to improve robustness against adversarial attacks while maintaining high accuracy on clean data. Our method introduces…

Machine Learning · Computer Science 2024-10-28 Shudian Zhao , Jan Kronqvist

Classifying and analyzing human cells is a lengthy procedure, often involving a trained professional. In an attempt to expedite this process, an active area of research involves automating cell classification through use of deep…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Reece Walsh , Mohamed H. Abdelpakey , Mohamed S. Shehata , Mostafa M. Mohamed

Few-shot classification aims to learn to classify new object categories well using only a few labeled examples. Transferring feature representations from other models is a popular approach for solving few-shot classification problems. In…

Computer Vision and Pattern Recognition · Computer Science 2022-09-07 Chun-Nam Yu , Yi Xie

We develop an approach for estimating models described via conditional moment restrictions, with a prototypical application being non-parametric instrumental variable regression. We introduce a min-max criterion function, under which the…

Econometrics · Economics 2020-06-15 Nishanth Dikkala , Greg Lewis , Lester Mackey , Vasilis Syrgkanis

Many machine learning algorithms and classifiers are available only via API queries as a ``black-box'' -- that is, the downstream user has no ability to change, re-train, or fine-tune the model on a particular target distribution. Indeed,…

Machine Learning · Computer Science 2025-03-05 Siddartha Devic , Nurendra Choudhary , Anirudh Srinivasan , Sahika Genc , Branislav Kveton , Gaurush Hiranandani

Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We propose a convex optimization for learning a…

Machine Learning · Statistics 2017-04-12 Flavio P. Calmon , Dennis Wei , Karthikeyan Natesan Ramamurthy , Kush R. Varshney

Training or finetuning large-scale language models (LLMs) requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks. One approach is to treat these models as black…

Computation and Language · Computer Science 2024-03-20 Danqing Luo , Chen Zhang , Yan Zhang , Haizhou Li

Learning a new task from a handful of examples remains an open challenge in machine learning. Despite the recent progress in few-shot learning, most methods rely on supervised pretraining or meta-learning on labeled meta-training data and…

Machine Learning · Computer Science 2022-10-10 Kuilin Chen , Chi-Guhn Lee

In this work we are interested in the problems of supervised learning and variable selection when the input-output dependence is described by a nonlinear function depending on a few variables. Our goal is to consider a sparse nonparametric…

Machine Learning · Statistics 2012-08-14 Lorenzo Rosasco , Silvia Villa , Sofia Mosci , Matteo Santoro , Alessandro verri

In the era of deep learning, understanding over-fitting phenomenon becomes increasingly important. It is observed that carefully designed deep neural networks achieve small testing error even when the training error is close to zero. One…

Machine Learning · Statistics 2018-12-04 Yue Xing , Qifan Song , Guang Cheng
‹ Prev 1 3 4 5 6 7 10 Next ›