Philip Greengard — accepted AI-conference papers

2026

A Network of Biologically Inspired Rectified Spectral Units (ReSUs) Learns Hierarchical Features Without Error Backpropagation

Shanshan Qin, Joshua L. Pughe-Sanford, Alexander Genkin, Pembe Gizem Ozdil, Philip Greengard, Anirvan M. Sengupta +1

AAAI 2026technical

We introduce a biologically inspired, multilayer neural architecture composed of Rectified Spectral Units (ReSUs). Each ReSU projects a recent window of its input history onto a canonical direction obtained via canonical correlation analysis (CCA) of previously observed past–future input pairs, and

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Neurons as Detectors of Coherent Sets in Sensory Dynamics

Joshua L. Pughe-Sanford, Xuehao Ding, Jason J Moore, Anirvan M. Sengupta, Charles Epstein, Philip Greengard +1

NeurIPS 2025poster

We model sensory streams as observations from high-dimensional stochastic dynamical systems and conceptualize sensory neurons as self-supervised learners of compact representations of such dynamics. From prior experience, neurons learn {\it coherent sets}—regions of stimulus state space whose trajec…

Cited by 1 Source ↗Scholar ↗

2024

LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning

Han Guo, Philip Greengard, Eric Xing, Yoon Kim

ICLR 2024poster

We propose a simple approach for memory-efficient adaptation of pretrained language models. Our approach uses an iterative algorithm to decompose each pretrained matrix into a high-precision low-rank component and a memory-efficient quantized component. During finetuning, the quantized componen…

Cited by 56 Source ↗PDF ↗code ↗Scholar ↗

2023

Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach

Han Guo, Philip Greengard, Hongyi Wang, Andrew Gelman, Yoon Kim, Eric Xing

ICLR 2023poster

The canonical formulation of federated learning treats it as a distributed optimization problem where the model parameters are optimized against a global loss function that decomposes across client loss functions. A recent alternative formulation instead treats federated learning as a distributed in…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗

2023

Learning to Grow Pretrained Models for Efficient Transformer Training

Peihao Wang, Rameswar Panda, Lucas Torroba Hennigen, Philip Greengard, Leonid Karlinsky, Rogerio Feris +3

ICLR 2023top-25%

Scaling transformers has led to significant breakthroughs in many domains, leading to a paradigm in which larger versions of existing models are trained and released on a periodic basis. New instances of such models are typically trained completely from scratch, despite the fact that they are often…

Cited by 67 Source ↗PDF ↗Scholar ↗