paper-with-me

Papers

Exponential Machines

2016-05-12 · Alexander Novikov, Mikhail Trofimov, Ivan Oseledets

Modeling interactions between features improves the performance of machine learning solutions in many domains (e.g. recommender systems or sentiment analysis). In this paper, we introduce Exponential Machines (ExM), a predictor that models all interactions of every order. The key idea is to represent an exponentially large tensor of parameters in a factorized format called Tensor Train (TT). The Tensor Train format regularizes the model and lets you control the number of underlying parameters. To train the model, we develop a stochastic Riemannian optimization procedure, which allows us to fit tensors with 2^160 entries. We show that the model achieves state-of-the-art performance on synthetic data with high-order interactions and that it works on par with high-order factorization machines on a recommender system dataset MovieLens 100K.

📄 PDF Abstract BibTeX arXiv:1605.03795

Code (3)

Bihaqo/exp-machines 공식 구현
emstoudenmire/TNML
jemisjoky/torchmps pytorch

Tasks

Recommendation SystemsRiemannian optimizationSentiment Analysis

Similar Papers 제목 키워드 기반

Sample Space Truncation on Boltzmann Machines

2020-10-19 · NeurIPS Workshop DL-IG 2020 12 · Mahito Sugiyama, Koji Tsuda, Hiroyuki Nakahara

We present a lightweight variant of Boltzmann machines via sample space truncation, called a truncated Boltzmann machine (TBM), which has not been investigated before while can be naturally introduced from the log-linear…

Universal representation by Boltzmann machines with Regularised Axons

2023-10-22 · Przemysław R. Grzybowski, Antoni Jankiewicz, Eloy Piñol, David Cirauqui 외

It is widely known that Boltzmann machines are capable of representing arbitrary probability distributions over the values of their visible neurons, given enough hidden ones. However, sampling -- and thus training -- the…

Retrieval

Tensor Network-Constrained Kernel Machines as Gaussian Processes

2024-03-28 · Frederiek Wesel, Kim Batselier

Tensor Networks (TNs) have recently been used to speed up kernel machines by constraining the model weights, yielding exponential computational and storage savings. In this paper we prove that the outputs of Canonical Po…

Gaussian ProcessesTensor Networks

Activation Functions, Statistics and Learning of Higher-Order Interactions in Restricted Boltzmann Machines

2026-05-18 · Giovanni di Sarra, Yasser Roudi arxiv

The great success of neural networks primarily arises from the presence of the large number of weight parameters combined with nonlinearities in the input-output relationship of single neurons. In this work, we study the…

Solving adversarial examples requires solving exponential misalignment

2026-03-03 · Alessandro Salvatore, Stanislav Fort, Surya Ganguli arxiv

Adversarial attacks - input perturbations imperceptible to humans that fool neural networks - remain both a persistent failure mode in machine learning, and a phenomenon with mysterious origins. To shed light, we define …

Adversarial Robustness