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.
EDCompress optimizes energy efficiency of CNN models on edge devices.
The paper proposes a dataflow-based approach to reduce energy consumption in deep neural networks without sacrificing performance.
Efficient method improves neural network device placement.
Adaptive financial dataflow system improves model robustness in dynamic markets.
System uses neural networks to prove program equivalence via rewrite rules.
Training neural network often uses a machine learning framework such as TensorFlow and Caffe2. These frameworks employ a dataflow model where the NN training is modeled as a directed graph composed of a set of nodes. Operations in neural network training are typically implemented by the frameworks as primitives and rep…
We review the current state of automatic differentiation (AD) for array programming in machine learning (ML), including the different approaches such as operator overloading (OO) and source transformation (ST) used for AD, graph-based intermediate representations for programs, and source languages. Based on these insig…
Recursive neural networks have widely been used by researchers to handle applications with recursively or hierarchically structured data. However, embedded control flow deep learning frameworks such as TensorFlow, Theano, Caffe2, and MXNet fail to efficiently represent and execute such neural networks, due to lack of s…
A new deep learning method using Boolean logic reduces training and inference energy.
This work optimizes deep learning training by combining data and model parallelism.
In recent years, there have been numerous developments towards solving multimodal tasks, aiming to learn a stronger representation than through a single modality. Certain aspects of the data can be particularly useful in this case - for example, correlations in the space or time domain across modalities - but should be…
Tiled Squeeze-and-Excite improves channel attention with local spatial context.
Paper proposes NASAIC framework for co-designing neural architectures and heterogeneous ASICs.