84 citations · 226 across the 21 of their papers we have counts for
21 papers
NRGPT: An Energy-based Alternative for GPT
Nima Dehmamy, Benjamin Hoover, Bishwajit Saha +3
Generative Pre-trained Transformer (GPT) architectures are the most popular design for language modeling. Energy-based modeling is a different paradigm that views inference as a dy…
Understanding Mode Connectivity via Parameter Space Symmetry
Bo Zhao, Nima Dehmamy, Robin Walters +1
Neural network minima are often connected by curves along which train and test loss remain nearly constant, a phenomenon known as mode connectivity. While this property has enabled…
Small Models, Smarter Learning: The Power of Joint Task Training
Csaba Both, Benjamin Hoover, Hendrik Strobelt +4
Multi-task learning improves generalization, but when does it reduce the model capacity required to learn? We provide a systematic study of how joint training affects the learning…
Discovering Symbolic Differential Equations with Symmetry Invariants
Jianke Yang, Manu Bhat, Bryan Hu +4
Discovering symbolic differential equations from data uncovers fundamental dynamical laws underlying complex systems. However, existing methods often struggle with the vast search…
AtlasD: Automatic Local Symmetry Discovery
Manu Bhat, Jonghyun Park, Jianke Yang +3
Existing symmetry discovery methods predominantly focus on global transformations across the entire system or space, but they fail to consider the symmetries in local neighborhoods…
DiffChip: Thermally Aware Chip Placement with Automatic Differentiation
Giuseppe Romano, Aakrati Jain, Nima Dehmamy +2
Chiplets are modular integrated circuits that can be combined to form a larger system, offering flexibility and performance enhancements. However, their dense packing often leads t…
Symmetry-Informed Governing Equation Discovery
Jianke Yang, Wang Rao, Nima Dehmamy +2
Despite the advancements in learning governing differential equations from observations of dynamical systems, data-driven methods are often unaware of fundamental physical laws, su…
Latent Space Symmetry Discovery
Jianke Yang, Nima Dehmamy, Robin Walters +1
Equivariant neural networks require explicit knowledge of the symmetry group. Automatic symmetry discovery methods aim to relax this constraint and learn invariance and equivarianc…
Generative Adversarial Symmetry Discovery
Jianke Yang, Robin Walters, Nima Dehmamy +1
Despite the success of equivariant neural networks in scientific applications, they require knowing the symmetry group a priori. However, it may be difficult to know which symmetry…
Symmetries, flat minima, and the conserved quantities of gradient flow
Bo Zhao, Iordan Ganev, Robin Walters +2
Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys. Yet, little is known about the theoretical ori…
Faster Optimization on Sparse Graphs via Neural Reparametrization
Nima Dehmamy, Csaba Both, Jianzhi Long +1
In mathematical optimization, second-order Newton's methods generally converge faster than first-order methods, but they require the inverse of the Hessian, hence are computational…
Symmetry Teleportation for Accelerated Optimization
Bo Zhao, Nima Dehmamy, Robin Walters +1
Existing gradient-based optimization methods update parameters locally, in a direction that minimizes the loss function. We study a different approach, symmetry teleportation, that…
Automatic Symmetry Discovery with Lie Algebra Convolutional Network
Nima Dehmamy, Robin Walters, Yanchen Liu +2
Existing equivariant neural networks require prior knowledge of the symmetry group and discretization for continuous groups. We propose to work with Lie algebras (infinitesimal gen…
Understanding the onset of hot streaks across artistic, cultural, and scientific careers
Lu Liu, Nima Dehmamy, Jillian Chown +2
Hot streaks dominate the main impact of creative careers. Despite their ubiquitous nature across a wide range of creative domains, it remains unclear if there is any regularity und…
3D Topology Transformation with Generative Adversarial Networks
Luca Stornaiuolo, Nima Dehmamy, Albert-László Barabási +1
Generation and transformation of images and videos using artificial intelligence have flourished over the past few years. Yet, there are only a few works aiming to produce creative…
Finding Patient Zero: Learning Contagion Source with Graph Neural Networks
Chintan Shah, Nima Dehmamy, Nicola Perra +4
Locating the source of an epidemic, or patient zero (P0), can provide critical insights into the infection's transmission course and allow efficient resource allocation. Existing m…
Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
Nima Dehmamy, Albert-László Barabási, Rose Yu
To deepen our understanding of graph neural networks, we investigate the representation power of Graph Convolutional Networks (GCN) through the looking glass of graph moments, a ke…
Separation of time scales and direct computation of weights in deep neural networks
Nima Dehmamy, Neda Rohani, Aggelos Katsaggelos
Artificial intelligence is revolutionizing our lives at an ever increasing pace. At the heart of this revolution is the recent advancements in deep neural networks (DNN), learning…
Crises and Physical Phases of a Bipartite Market Model
Nima Dehmamy, Sergey Buldyrev, Shlomo Havlin +2
We analyze the linear response of a market network to shocks based on the bipartite market model we introduced in an earlier paper, which we claimed to be able to identify the time…
Arbitrary degree distribution and high clustering in networks of locally interacting agents
Navid Dianati, Nima Dehmamy
Many real world networks, such as social networks, are primarily formed through local interactions between agents. Additionally, in contrast with common network models, social and…
Classical mechanics of economic networks
Nima Dehmamy, Sergey V. Buldyrev, Shlomo Havlin +2
Financial networks are dynamic. To assess their systemic importance to the world-wide economic network and avert losses we need models that take the time variations of the links an…