On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “einsum”

Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methodscs.LG

Simplifies convolutions using tensor networks and einsum for efficient second-order methods.

problem Complexity in analyzing and applying convolutions in deep learning.

method Viewing convolutions as tensor networks, drawing diagrams, and using einsum for efficient computation.

result Accelerates a KFAC variant up to 4.5x with reduced memory overhead.

tensor networks convolutions einsum second-order methods autodiff

2023-07-05abs ↗pdf ↗

Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuitscs.LG

EiNets improve PCs for scalable probabilistic modeling.

problem Scalability issues in training PCs on real-world data.

method Combining einsum operations for speedups and memory savings; simplifying EM for PCs.

result EiNets can scale to large datasets like SVHN and CelebA.

Probabilistic circuits Einsum Networks Scalability Efficient inference Deep learning

2020-04-13abs ↗pdf ↗

Near-Universal Multiplicative Updates for Nonnegative Einsum Factorizationstat.ML

NNEinFact fits any nonnegative tensor factorization quickly and accurately.

problem Limited user-friendly tools for fitting tailored nonnegative tensor factorizations.

method NNEinFact is an einsum-based multiplicative update algorithm that fits any nonnegative tensor factorization.

result NNEinFact converges to a stationary point of the loss, supports missing data, and fits tensors with hundreds of millions of entries in seconds.

tensor factorization nonnegative tensors multiplicative updates einsum gradient-based methods

2026-02-02abs ↗pdf ↗

pLSTM: parallelizable Linear Source Transition Mark networkscs.LG

pLSTM tackles long-range language modeling and computer vision tasks with parallelizable linear source transition mark networks.

problem Challenges of existing recurrent architectures in handling sequences and multi-dimensional data.

method Introduces pLSTM, a parallelizable linear source transition mark network for linear graphs and DAGs, addressing vanishing/exploding activation/gradient issues.

result pLSTM outperforms Transformers in long-range tasks like arrow-pointing extrapolation and image size extrapolation.

pLSTM parallelizable linear source transition Mark networks vanishing/exploding gradient

2025-06-13abs ↗pdf ↗