English
Related papers

Related papers: Freezing and Sleeping: Tracking Experts that Learn…

200 papers

Mixture-of-Experts (MoE) is a widely popular model for ensemble learning and is a basic building block of highly successful modern neural networks as well as a component in Gated Recurrent Units (GRU) and Attention networks. However,…

Machine Learning · Computer Science 2019-06-10 Ashok Vardhan Makkuva , Sewoong Oh , Sreeram Kannan , Pramod Viswanath

Linear programming has been practically solved mainly by simplex and interior point methods. Compared with the weakly polynomial complexity obtained by the interior point methods, the existence of strongly polynomial bounds for the length…

Optimization and Control · Mathematics 2024-04-23 Tianhao Liu , Shanwen Pu , Dongdong Ge , Yinyu Ye

Federated Bayesian neural networks require fixing a prior on the model parameters together with a likelihood. Eliciting meaningful priors on the weight space of modern overparameterized models is notoriously difficult, and misspecification…

Machine Learning · Computer Science 2026-05-19 Boning Zhang , Matteo Zecchin , Mingzhao Guo , Dongzhu Liu , Osvaldo Simeone

Catastrophic forgetting is a challenge issue in continual learning when a deep neural network forgets the knowledge acquired from the former task after learning on subsequent tasks. However, existing methods try to find the joint…

Machine Learning · Computer Science 2018-12-06 Jian Peng , Jiang Hao , Zhuo Li , Enqiang Guo , Xiaohong Wan , Deng Min , Qing Zhu , Haifeng Li

Mixture of experts (MoE), introduced over 20 years ago, is the simplest gated modular neural network architecture. There is renewed interest in MoE because the conditional computation allows only parts of the network to be used during each…

Machine Learning · Computer Science 2023-03-01 Yamuna Krishnamurthy , Chris Watkins , Thomas Gaertner

Generating crisp, i.e., one-pixel-wide, edge maps remains one of the fundamental challenges in edge detection, affecting both traditional and learning-based methods. To obtain crisp edges, most existing approaches rely on two hand-crafted…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Bedrettin Cetinkaya , Sinan Kalkan , Emre Akbas

We introduce a Model Predictive Control (MPC) framework for training deep neural networks, systematically unifying the Back-Propagation (BP) and Forward-Forward (FF) algorithms. At the same time, it gives rise to a range of intermediate…

Machine Learning · Computer Science 2024-10-01 Lianhai Ren , Qianxiao Li

When dealing with time series with complex non-stationarities, low retrospective regret on individual realizations is a more appropriate goal than low prospective risk in expectation. Online learning algorithms provide powerful guarantees…

Machine Learning · Statistics 2011-06-30 Cosma Rohilla Shalizi , Abigail Z. Jacobs , Kristina Lisa Klinkner , Aaron Clauset

Effective caching is crucial for the performance of modern-day computing systems. A key optimization problem arising in caching -- which item to evict to make room for a new item -- cannot be optimally solved without knowing the future.…

Machine Learning · Computer Science 2021-06-29 Jakub Chłędowski , Adam Polak , Bartosz Szabucki , Konrad Zolna

Multi-Modal Entity Alignment aims to discover identical entities across heterogeneous knowledge graphs. While recent studies have delved into fusion paradigms to represent entities holistically, the elimination of features irrelevant to…

Computation and Language · Computer Science 2024-07-24 Yani Huang , Xuefeng Zhang , Richong Zhang , Junfan Chen , Jaein Kim

Learning the parameters of Partially Observable Markov Decision Processes (POMDPs) from limited data is a significant challenge. We introduce the Fuzzy MAP EM algorithm, a novel approach that incorporates expert knowledge into the parameter…

Machine Learning · Computer Science 2025-11-19 Marco Locatelli , Arjen Hommersom , Roberto Clemens Cerioli , Daniela Besozzi , Fabio Stella

Parameter-efficient transfer learning (PETL) has emerged as a pivotal paradigm for adapting pre-trained foundation models to downstream tasks, significantly reducing trainable parameters yet suffering from substantial memory overhead caused…

Machine Learning · Computer Science 2026-05-07 Yutong Zhang , Zimeng Wu , Shangcai Liao , Shujiang Wu , Jiaxin Chen

In Reinforcement Learning (RL), regularization has emerged as a popular tool both in theory and practice, typically based either on an entropy bonus or a Kullback-Leibler divergence that constrains successive policies. In practice, these…

Machine Learning · Computer Science 2025-06-18 Alena Shilova , Alex Davey , Brahim Driss , Riad Akrour

Model merging offers an efficient way to combine pre-trained neural networks but often suffers from inconsistent performance, especially when merging models with different initializations. We identify the ``vanishing feature'' phenomenon,…

Machine Learning · Computer Science 2025-02-28 Xingyu Qu , Samuel Horvath

The closest pair of points problem or closest pair problem (CPP) is an important problem in computational geometry where we have to find a pair of points from a set of points in metric space with the smallest distance between them. This…

Data Structures and Algorithms · Computer Science 2020-08-03 Subrata Saha , Ahmed Soliman , Sanguthevar Rajasekaran

The extreme learning machine needs a large number of hidden nodes to generalize a single hidden layer neural network for a given training data-set. The need for more number of hidden nodes suggests that the neural-network is memorizing…

Machine Learning · Computer Science 2019-10-08 Dibyasundar Das , Deepak Ranjan Nayak , Ratnakar Dash , Banshidhar Majhi

The real-world traffic networks undergo expansion through the installation of new sensors, implying that the traffic patterns continually evolve over time. Incrementally training a model on the newly added sensors would make the model…

Machine Learning · Computer Science 2024-06-06 Sanghyun Lee , Chanyoung Park

Sparse mixture of experts provides larger model capacity while requiring a constant computational overhead. It employs the routing mechanism to distribute input tokens to the best-matched experts according to their hidden representations.…

Computation and Language · Computer Science 2022-10-13 Zewen Chi , Li Dong , Shaohan Huang , Damai Dai , Shuming Ma , Barun Patra , Saksham Singhal , Payal Bajaj , Xia Song , Xian-Ling Mao , Heyan Huang , Furu Wei

Prediction with expert advice is a foundational problem in online learning. In instances with $T$ rounds and $n$ experts, the classical Multiplicative Weights Update method suffers at most $\sqrt{(T/2)\ln n}$ regret when $T$ is known…

Machine Learning · Computer Science 2022-03-16 Laura Greenstreet , Nicholas J. A. Harvey , Victor Sanches Portella

Large-scale pre-trained models (PTMs) provide remarkable zero-shot classification capability covering a wide variety of object classes. However, practical applications do not always require the classification of all kinds of objects, and…

Machine Learning · Computer Science 2024-11-04 Yusuke Kuwana , Yuta Goto , Takashi Shibata , Go Irie