English
Related papers

Related papers: SAEs $\textit{Can}$ Improve Unlearning: Dynamic Sp…

200 papers

Deep reinforcement learning (RL) algorithms frequently require prohibitive interaction experience to ensure the quality of learned policies. The limitation is partly because the agent cannot learn much from the many low-quality trials in…

Machine Learning · Computer Science 2020-04-24 Keting Lu , Shiqi Zhang , Xiaoping Chen

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Computation and Language · Computer Science 2025-02-27 Sumanta Bhattacharyya , Pedram Rooshenas

Deep Neural Networks (DNNs) are a critical component for self-driving vehicles. They achieve impressive performance by reaping information from high amounts of labeled data. Yet, the full complexity of the real world cannot be encapsulated…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Julien Rebut , Andrei Bursuc , Patrick Pérez

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Machine Learning · Computer Science 2020-07-08 Tianxiao Shen , Jonas Mueller , Regina Barzilay , Tommi Jaakkola

This paper revisits two prominent adaptive filtering algorithms, namely recursive least squares (RLS) and equivariant adaptive source separation (EASI), through the lens of algorithm unrolling. Building upon the unrolling methodology, we…

Signal Processing · Electrical Eng. & Systems 2023-11-17 Zahra Esmaeilbeig , Mojtaba Soltanalian

Machine unlearning addresses the problem of updating a machine learning model/system trained on a dataset $S$ so that the influence of a set of deletion requests $U \subseteq S$ on the unlearned model is minimized. The gold standard…

Machine Learning · Computer Science 2025-06-09 Linda Lu , Ayush Sekhari , Karthik Sridharan

In this work, a non-gradient descent learning (NGDL) scheme was proposed for deep feedforward neural networks (DNN). It is known that an autoencoder can be used as the building blocks of the multi-layer perceptron (MLP) DNN, the MLP is…

Machine Learning · Computer Science 2021-08-25 P. Guo , K. Wang , X. L. Zhou

Stochastic gradient descent (SGD) is a standard optimization method to minimize a training error with respect to network parameters in modern neural network learning. However, it typically suffers from proliferation of saddle points in the…

Machine Learning · Computer Science 2017-11-23 Haiping Huang , Taro Toyoizumi

Machine unlearning is the process through which a deployed machine learning model is made to forget about some of its training data points. While naively retraining the model from scratch is an option, it is almost always associated with…

Machine Learning · Computer Science 2022-03-03 Anvith Thudi , Gabriel Deza , Varun Chandrasekaran , Nicolas Papernot

Some of the threats in the dynamic environment include the unpredictability of the motion of objects and interferences to the robotic grasp. In such conditions the traditional supervised and reinforcement learning approaches are ill suited…

Robotics · Computer Science 2024-10-18 Ankit Shaw

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Machine Learning · Computer Science 2026-02-03 Jack Gallifant , Shan Chen , Kuleen Sasse , Hugo Aerts , Thomas Hartvigsen , Danielle S. Bitterman

Distributed Deep Learning (DDL) is essential for large-scale Deep Learning (DL) training. Synchronous Stochastic Gradient Descent (SSGD) 1 is the de facto DDL optimization method. Using a sufficiently large batch size is critical to…

Machine Learning · Computer Science 2021-12-03 Wei Zhang , Mingrui Liu , Yu Feng , Xiaodong Cui , Brian Kingsbury , Yuhai Tu

Sparse autoencoders (SAEs) \citep{bricken2023monosemanticity,gao2024scalingevaluatingsparseautoencoders} rely on dictionary learning to extract interpretable features from neural networks at scale in an unsupervised manner, with…

Machine Learning · Computer Science 2025-05-02 Hans Peter , Anders Søgaard

Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward…

Machine Learning · Computer Science 2022-01-20 An Xu , Zhouyuan Huo , Heng Huang

Machine unlearning has raised significant interest with the adoption of laws ensuring the ``right to be forgotten''. Researchers have provided a probabilistic notion of approximate unlearning under a similar definition of Differential…

Machine Learning · Computer Science 2025-09-25 Eli Chien , Haoyu Wang , Ziang Chen , Pan Li

Sparse Autoencoders (SAEs) have proven to be powerful tools for interpreting neural networks by decomposing hidden representations into disentangled, interpretable features via sparsity constraints. However, conventional SAEs are…

The ability of large language models (LLMs) to follow instructions is crucial for their practical applications, yet the underlying mechanisms remain poorly understood. This paper presents a novel framework that leverages sparse autoencoders…

Machine Learning · Computer Science 2025-02-18 Zirui He , Haiyan Zhao , Yiran Qiao , Fan Yang , Ali Payani , Jing Ma , Mengnan Du

Machine learning models often incorporate vast amounts of data, raising significant privacy concerns. Machine unlearning, the ability to remove the influence of specific data points from a trained model, addresses these concerns. This paper…

Machine Learning · Computer Science 2024-06-14 David Zagardo

Large language models (LLMs) are now ubiquitous in user-facing applications, yet they still generate undesirable toxic outputs, including profanity, vulgarity, and derogatory remarks. Although numerous detoxification methods exist, most…

Computation and Language · Computer Science 2025-10-24 Agam Goyal , Vedant Rathi , William Yeh , Yian Wang , Yuen Chen , Hari Sundaram

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba