Neural LoFi models deep learning as layer-wise spectral filtering that selects maximal low-degree correlations, yielding a tractable surrogate for hierarchical representation learning beyond the lazy regime.
Pytorch: An imperative style, high- performance deep learning library.Advances in neural information processing systems, 32
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
other 1
citation-polarity summary
representative citing papers
LightStim automates DEM construction for QEC protocols via an augmented Pauli tableau during compilation, matching public tools on detector counts and error rates while enabling new cross-code designs.
FlashAttention reduces GPU high-bandwidth memory accesses in self-attention via tiling, delivering exact attention with lower IO complexity, 2-3x wall-clock speedups on models like GPT-2, and the ability to train on sequences up to 64K long.
A C++ Dec-POMDP simulator using data-oriented design and zero-copy PyTorch integration achieves up to 33 million steps per second on a 16-core CPU, enabling multi-agent policy training in minutes with PPO, DQN, and SAC.
PINNACLE is an open-source framework for classical and quantum PINNs that supplies modular training methods and benchmarks showing high sensitivity to architecture choices plus parameter-efficiency gains in some hybrid quantum regimes.
EmDT combines UMAP clustering with a Transformer-based diffusion process to create synthetic fraud samples that improve XGBoost classification on credit card fraud data while preserving correlations and privacy.
Higher-order LaSDI uses a high-order finite-difference scheme and rollout loss to improve long-term prediction accuracy in reduced-order models for parameterized PDEs, shown on the 2D Burgers equation.
citing papers explorer
-
Deep Learning as Neural Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning
Neural LoFi models deep learning as layer-wise spectral filtering that selects maximal low-degree correlations, yielding a tractable surrogate for hierarchical representation learning beyond the lazy regime.
-
LightStim: A Framework for QEC Protocol Evaluation and Prototyping with Automated DEM Construction
LightStim automates DEM construction for QEC protocols via an augmented Pauli tableau during compilation, matching public tools on detector counts and error rates while enabling new cross-code designs.
-
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
FlashAttention reduces GPU high-bandwidth memory accesses in self-attention via tiling, delivering exact attention with lower IO complexity, 2-3x wall-clock speedups on models like GPT-2, and the ability to train on sequences up to 64K long.
-
A High-Throughput Compute-Efficient POMDP Hide-And-Seek-Engine (HASE) for Multi-Agent Operations
A C++ Dec-POMDP simulator using data-oriented design and zero-copy PyTorch integration achieves up to 33 million steps per second on a 16-core CPU, enabling multi-agent policy training in minutes with PPO, DQN, and SAC.
-
PINNACLE: An Open-Source Computational Framework for Classical and Quantum PINNs
PINNACLE is an open-source framework for classical and quantum PINNs that supplies modular training methods and benchmarks showing high sensitivity to architecture choices plus parameter-efficiency gains in some hybrid quantum regimes.
-
EmDT: Embedding Diffusion Transformer for Tabular Data Generation in Fraud Detection
EmDT combines UMAP clustering with a Transformer-based diffusion process to create synthetic fraud samples that improve XGBoost classification on credit card fraud data while preserving correlations and privacy.
-
Higher-Order LaSDI: Reduced Order Modeling with Multiple Time Derivatives
Higher-order LaSDI uses a high-order finite-difference scheme and rollout loss to improve long-term prediction accuracy in reduced-order models for parameterized PDEs, shown on the 2D Burgers equation.