English
Related papers

Related papers: Sign Lock-In: Randomly Initialized Weight Signs Pe…

200 papers

Learning-based lossy image compression usually involves the joint optimization of rate-distortion performance. Most existing methods adopt spatially invariant bit length allocation and incorporate discrete entropy approximation to constrain…

Computer Vision and Pattern Recognition · Computer Science 2019-04-02 Mu Li , Wangmeng Zuo , Shuhang Gu , Jane You , David Zhang

We investigate the expressive power of depth-2 bandlimited random neural networks. A random net is a neural network where the hidden layer parameters are frozen with random assignment, and only the output layer parameters are trained by…

Machine Learning · Computer Science 2023-06-01 Ming Li , Sho Sonoda , Feilong Cao , Yu Guang Wang , Jiye Liang

The expicit restricted isometry property (RIP) measurement matrices are needed in practical application of compressed sensing in signal processing. RIP matrices from Reed-Solomon codes, BCH codes, orthogonal codes, expander graphs have been…

Information Theory · Computer Science 2015-06-15 Liqing Xu , Hao Chen

Standard models of biologically realistic or biologically inspired reinforcement learning employ a global error signal, which implies the use of shallow networks. On the other hand, error backpropagation allows the use of networks with…

Machine Learning · Computer Science 2023-09-14 Sama Daryanavard , Bernd Porr

Pruning the weights of randomly initialized neural networks plays an important role in the context of lottery ticket hypothesis. Ramanujan et al. (2020) empirically showed that only pruning the weights can achieve remarkable performance…

Machine Learning · Computer Science 2022-04-06 Daiki Chijiwa , Shin'ya Yamaguchi , Yasutoshi Ida , Kenji Umakoshi , Tomohiro Inoue

This paper studies the stability of some reconstruction algorithms for compressed sensing in terms of the bit precision. Considering the fact that practical digital systems deal with discretized signals, we motivate the importance of the…

Information Theory · Computer Science 2009-01-16 Ehsan Ardestanizadeh , Mahdi Cheraghchi , Amin Shokrollahi

Prompt injection attacks pose significant risks to language model safety, yet existing defenses are typically evaluated using classification performance. We show that high detection performance does not imply representational robustness.…

Cryptography and Security · Computer Science 2026-05-20 Becky Mashaido , Tapadhir Das

We study a basic question about cryptographic watermarking for generative models: how reliable can a watermark remain when an adversary is allowed to corrupt the encoded signal? To address this question, we introduce a minimal coding…

Cryptography and Security · Computer Science 2026-05-05 Danilo Francati , Yevin Nikhel Goonatilake , Shubham Pawar , Daniele Venturi , Giuseppe Ateniese

Deep neural networks have shown impressive performance in supervised learning, enabled by their ability to fit well to the provided training data. However, their performance is largely dependent on the quality of the training data and often…

Machine Learning · Computer Science 2021-11-11 Abhishek Kumar , Ehsan Amid

Integer-forcing source coding has been proposed as a low-complexity method for compression of distributed correlated Gaussian sources. In this scheme, each encoder quantizes its observation using the same fine lattice and reduces the result…

Information Theory · Computer Science 2019-06-05 Elad Domanovitz , Uri Erez

Autoencoders are a popular model in many branches of machine learning and lossy data compression. However, their fundamental limits, the performance of gradient methods and the features learnt during optimization remain poorly understood,…

Machine Learning · Computer Science 2023-01-12 Alexander Shevchenko , Kevin Kögler , Hamed Hassani , Marco Mondelli

In recent years, non-convex optimization problems are more often described by generalized $(L_0, L_1)$-smoothness assumption rather than standard one. Meanwhile, severely corrupted data used in these problems has increased the demand for…

Optimization and Control · Mathematics 2025-05-28 Nikita Kornilov , Philip Zmushko , Andrei Semenov , Mark Ikonnikov , Alexander Gasnikov , Alexander Beznosikov

Regularization techniques such as L2 regularization (Weight Decay) and Dropout are fundamental to training deep neural networks, yet their underlying physical mechanisms regarding feature frequency selection remain poorly understood. In…

Machine Learning · Computer Science 2025-12-30 Jiahao Lu

Robustness of deep neural networks against adversarial perturbations is a pressing concern motivated by recent findings showing the pervasive nature of such vulnerabilities. One method of characterizing the robustness of a neural network…

Machine Learning · Statistics 2021-03-15 Hisham Husain , Borja Balle

Neural networks excel across a wide range of tasks, yet remain black boxes. In particular, how their internal representations are shaped by the complexity of the input data and the problems they solve remains obscure. In this work, we…

Machine Learning · Computer Science 2026-05-12 Robert Jankowski , Filippo Radicchi , M. Ángeles Serrano , Marián Boguñá , Santo Fortunato

Random backpropagation (RBP) is a variant of the backpropagation algorithm for training neural networks, where the transpose of the forward matrices are replaced by fixed random matrices in the calculation of the weight updates. It is…

Machine Learning · Computer Science 2017-12-25 Pierre Baldi , Peter Sadowski , Zhiqin Lu

Non-volatile memory, such as resistive RAM (RRAM), is an emerging energy-efficient storage, especially for low-power machine learning models on the edge. It is reported, however, that the bit error rate of RRAMs can be up to 3.3% in the…

Signal compression based on implicit neural representation (INR) is an emerging technique to represent multimedia signals with a small number of bits. While INR-based signal compression achieves high-quality reconstruction for relatively…

Image and Video Processing · Electrical Eng. & Systems 2024-12-31 Takuya Fujihashi , Toshiaki Koike-Akino

We consider the task of deriving a key with high HILL entropy from an unpredictable source. Previous to this work, the only known way to transform unpredictability into a key that was $\eps$ indistinguishable from having min-entropy was via…

Cryptography and Security · Computer Science 2015-04-29 Maciej Skorski , Alexander Golovnev , Krzysztof Pietrzak

We present some novel, straightforward methods for training the connection graph of a randomly initialized neural network without training the weights. These methods do not use hyperparameters defining cutoff thresholds and therefore remove…

Machine Learning · Computer Science 2020-11-18 Cristian Ivan , Razvan Florian
‹ Prev 1 4 5 6 7 8 10 Next ›