AIConfPaper
← Search

Hadi Mohaghegh Dolatabadi

6 accepted papers

2026

Factored Gossip DiLoCo: Reducing Blocking Communication within DiLoCo

Chamin Hewa Koneputugodage, Thalaiyasingam Ajanthan, Sameera Ramasinghe, Hadi Mohaghegh Dolatabadi, Shamane Siriwardhana, Gil Avraham +4
ICML 2026poster

To make large-scale distributed training practical outside high-bandwidth datacenters, we must reduce blocking, high-volume synchronization. While DiLoCo communicates infrequently, its outer synchronization remains bandwidth-heavy and brittle to stragglers and transient failures. We relax exact sync…

Cited by 0Source ↗Scholar ↗
2026

Taming Curvature: Architecture Warm-up for Stable Transformer Training

Sameera Ramasinghe, Thalaiyasingam Ajanthan, Hadi Mohaghegh Dolatabadi, Chamin P Hewa Koneputugodage, Gil Avraham, Violetta Shevchenko +3
ICLR 2026poster

Training billion-parameter Transformers is often brittle, with transient loss spikes and divergence that waste compute. Even though the recently developed Edge of Stability (EoS) theory provides a powerful tool to understand and control the stability of optimization methods via the (preconditioned)…

Cited by 0Source ↗Scholar ↗
2025

Mixtures of Subspaces for Bandwidth Efficient Context Parallel Training

Sameera Ramasinghe, Thalaiyasingam Ajanthan, Hadi Mohaghegh Dolatabadi, Gil Avraham, Violetta Shevchenko, Yan Zuo +2
NeurIPS 2025poster

Pretraining language models with extended context windows enhances their ability to leverage rich information during generation. Existing methods split input sequences into chunks, broadcast them across multiple devices, and compute attention block by block which incurs significant communication ove…

Cited by 0Source ↗Scholar ↗
2025

Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization

Alexander Long, Chamin P Hewa Koneputugodage, Thalaiyasingam Ajanthan, Yan Zuo, Gil Avraham, Violetta Shevchenko +2
NeurIPS 2025poster

We consider a decentralized setup in which the participants collaboratively train and serve a large neural network, and where each participant only processes a subset of the model. In this setup, we explore the possibility of unmaterializable weights, where a full weight set is never available to a…

Cited by 0Source ↗Scholar ↗
2020

AdvFlow: Inconspicuous Black-box Adversarial Attacks using Normalizing Flows

Hadi Mohaghegh Dolatabadi, Sarah Erfani, Christopher Leckie
NeurIPS 2020poster

Deep learning classifiers are susceptible to well-crafted, imperceptible variations of their inputs, known as adversarial attacks. In this regard, the study of powerful attack models sheds light on the sources of vulnerability in these classifiers, hopefully leading to more robust ones. In this pape…

Cited by 70Source ↗PDF ↗code ↗Scholar ↗
2020

Invertible Generative Modeling using Linear Rational Splines

Hadi Mohaghegh Dolatabadi, Sarah Erfani, Christopher Leckie
AISTATS 2020poster

Normalizing flows attempt to model an arbitrary probability distribution through a set of invertible mappings. These transformations are required to achieve a tractable Jacobian determinant that can be used in high-dimensional scenarios. The first normalizing flow designs used coupling layer mapping…

Cited by 53Source ↗PDF ↗code ↗Scholar ↗