English
Related papers

Related papers: Beyond Lazy Training for Over-parameterized Tensor…

200 papers

Modern neural networks are typically trained in an over-parameterized regime where the parameters of the model far exceed the size of the training data. Such neural networks in principle have the capacity to (over)fit any set of labels…

Machine Learning · Computer Science 2019-07-05 Mingchen Li , Mahdi Soltanolkotabi , Samet Oymak

Tensor rank and low-rank tensor decompositions have many applications in learning and complexity theory. Most known algorithms use unfoldings of tensors and can only handle rank up to $n^{\lfloor p/2 \rfloor}$ for a $p$-th order tensor in…

Data Structures and Algorithms · Computer Science 2015-04-23 Rong Ge , Tengyu Ma

While post-training model compression can greatly reduce the inference cost of a deep neural network, uncompressed training still consumes a huge amount of hardware resources, run-time and energy. It is highly desirable to directly train a…

Machine Learning · Computer Science 2021-10-05 Cole Hawkins , Xing Liu , Zheng Zhang

The machine learning of lattice operators has three possible bottlenecks. From a statistical standpoint, it is necessary to design a constrained class of operators based on prior information with low bias, and low complexity relative to the…

Machine Learning · Computer Science 2024-06-21 Diego Marcondes , Junior Barrera

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

The prevalent fully-connected tensor network (FCTN) has achieved excellent success to compress data. However, the FCTN decomposition suffers from slow computational speed when facing higher-order and large-scale data. Naturally, there…

Machine Learning · Computer Science 2022-10-20 Peilin Yang , Weijun Sun , Qibin Zhao , Guoxu Zhou

Low-rank regularization (LRR) has been widely applied in various machine learning tasks, but the associated optimization is challenging. Directly optimizing the rank function under constraints is NP-hard in general. To overcome this…

Machine Learning · Computer Science 2025-05-22 Naiqi Li , Yuqiu Xie , Peiyuan Liu , Tao Dai , Yong Jiang , Shu-Tao Xia

It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings. There is minimal theoretical understanding of empirical success, e.g., why fine-tuning a model with $10^8$ or more…

Machine Learning · Computer Science 2023-06-07 Sadhika Malladi , Alexander Wettig , Dingli Yu , Danqi Chen , Sanjeev Arora

In the training of over-parameterized model functions via gradient descent, sometimes the parameters do not change significantly and remain close to their initial values. This phenomenon is called lazy training, and motivates consideration…

Quantum Physics · Physics 2023-05-03 Erfan Abedi , Salman Beigi , Leila Taghavi

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper…

Machine Learning · Statistics 2020-06-18 Kenji Kawaguchi , Jiaoyang Huang

Effective modeling of heterogeneous subpopulations presents a significant challenge due to variations in individual characteristics and behaviors. This paper proposes a novel approach to address this issue through multi-task learning (MTL)…

Machine Learning · Computer Science 2025-08-22 Elif Konyar , Mostafa Reisi Gahrooei , Kamran Paynabar

In practical instances of nonconvex matrix factorization, the rank of the true solution $r^{\star}$ is often unknown, so the rank $r$ of the model can be overspecified as $r>r^{\star}$. This over-parameterized regime of matrix factorization…

Optimization and Control · Mathematics 2025-04-15 Gavin Zhang , Salar Fattahi , Richard Y. Zhang

Tensor networks have demonstrated significant value for machine learning in a myriad of different applications. However, optimizing tensor networks using standard gradient descent has proven to be difficult in practice. Tensor networks…

Machine Learning · Computer Science 2022-03-08 Fergus Barratt , James Dborin , Lewis Wright

The so-called block-term decomposition (BTD) tensor model, especially in its rank-$(L_r,L_r,1)$ version, has been recently receiving increasing attention due to its enhanced ability of representing systems and signals that are composed of…

Methodology · Statistics 2022-05-04 Paris V. Giampouras , Athanasios A. Rontogiannis , Eleftherios Kofidis

Due to the substantial scale of Large Language Models (LLMs), the direct application of conventional compression methodologies proves impractical. The computational demands associated with even minimal gradient updates present challenges,…

Machine Learning · Computer Science 2023-12-13 Arnav Chavan , Nahush Lele , Deepak Gupta

When an online learning algorithm is used to estimate the unknown parameters of a model, the signals interacting with the parameter estimates should not decay too quickly for the optimal values to be discovered correctly. This requirement…

Machine Learning · Computer Science 2019-11-05 Kamil Nar , S. Shankar Sastry

We propose a new numerical algorithm for computing the tensor rank decomposition or canonical polyadic decomposition of higher-order tensors subject to a rank and genericity constraint. Reformulating this computational problem as a system…

Numerical Analysis · Mathematics 2024-07-02 Simon Telen , Nick Vannieuwenhoven

The goal of this paper is to find a low-rank approximation for a given tensor. Specifically, we give a computable strategy on calculating the rank of a given tensor, based on approximating the solution to an NP-hard problem. In this paper,…

Numerical Analysis · Mathematics 2016-10-20 Xiaofei Wang , Carmeliza Navasca

One of the main issues in computing a tensor decomposition is how to choose the number of rank-one components, since there is no finite algorithms for determining the rank of a tensor. A commonly used approach for this purpose is to find a…

Computer Vision and Pattern Recognition · Computer Science 2023-09-15 Claudio Turchetti

This paper rigorously shows how over-parameterization changes the convergence behaviors of gradient descent (GD) for the matrix sensing problem, where the goal is to recover an unknown low-rank ground-truth matrix from near-isotropic linear…

Machine Learning · Computer Science 2023-11-27 Nuoya Xiong , Lijun Ding , Simon S. Du
‹ Prev 1 4 5 6 7 8 10 Next ›