Author name cluster

Torsten Hoefler

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

16 papers

2 author rows

YNIMG Journal 2025 Journal Article

Atlas-independent brain connectome analysis at voxel-level granularity: graph convolutional networks for etiology classification in newborns

Anna Speckert
Lukas Gianinazzi
Sepp Kollmorgen
Cornelia Hagmann
Patrice Grehten
Raimund Kottke
Giancarlo Natalucci
Beatrice Latal

Early identification of altered brain networks in neonates at risk for neurodevelopmental impairments is critical for timely intervention and improving outcomes. This study explores the potential of graph neural networks (GNNs) applied to structural brain connectomes at the voxel level granularity to classify neonatal connectomes by their underlying etiology: 51 children with congenital heart disease (CHD), 100 children born very preterm (PB), and 43 children with spina bifida aperta (SBA). Leveraging the flexibility of voxel-level parcellation, we captured fine-grained connectomic differences that improved classification performance (F1 = 0.78) compared to both atlas-based methods (F1 = 0.62) and a multilayer perceptron baseline model (F1 = 0.69). This approach enables subject-specific parcellation without the need for predefined anatomical templates, facilitating the analysis of diverse brain morphologies and age ranges. Attribution analysis using integrated gradients provided interpretable insights into etiology-specific connectomic patterns, highlighting regions of potential neurodevelopmental importance, such as the Rolandic operculum, inferior parietal lobule, and inferior frontal gyrus. Lateralized attribution patterns in PB reflected known neurodevelopmental alterations, underscoring the value of interpretable graph learning for understanding etiology-specific connectomic features. This work represents an important step toward atlas-independent connectome analysis, offering a novel framework for studying diverse neonatal populations and advancing our understanding of early brain development.

Details DOI

NeurIPS Conference 2025 Conference Paper

HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs

Saleh Ashkboos
Mahdi Nikdan
Rush Tabesh
Roberto Castro
Torsten Hoefler
Dan Alistarh

Quantized training of Large Language Models (LLMs) remains an open challenge, as maintaining accuracy while performing all matrix multiplications in low precision has proven difficult. This is particularly the case when fine-tuning pre-trained models, which can have large weight, activation, and error (output gradient) outlier values that make lower-precision optimization difficult. To address this, we present HALO, a new quantization-aware training approach for Transformers that enables accurate and efficient low-precision training by combining 1) strategic placement of Hadamard rotations in both forward and backward passes, which mitigate outliers, 2) high-performance kernel support, and 3) FSDP integration for low-precision communication. Our approach ensures that all large matrix multiplications during the forward and backward passes are executed in lower precision. Applied to LLaMa models, HALO achieves near-full-precision-equivalent results during fine-tuning on various tasks, while delivering up to 1. 41x end-to-end speedup for full fine-tuning on RTX 4090 GPUs. HALO efficiently supports both standard and parameter-efficient fine-tuning (PEFT). Our results demonstrate the first practical approach to fully quantized LLM fine-tuning that maintains accuracy in INT8 and FP6 precision, while delivering performance benefits.

PDF Details

ICML Conference 2024 Conference Paper

DiffDA: a Diffusion model for weather-scale Data Assimilation

Langwen Huang
Lukas Gianinazzi
Yuejiang Yu
Peter D. Düben
Torsten Hoefler

The generation of initial conditions via accurate data assimilation is crucial for weather forecasting and climate modeling. We propose DiffDA as a denoising diffusion model capable of assimilating atmospheric variables using predicted states and sparse observations. Acknowledging the similarity between a weather forecast model and a denoising diffusion model dedicated to weather applications, we adapt the pretrained GraphCast neural network as the backbone of the diffusion model. Through experiments based on simulated observations from the ERA5 reanalysis dataset, our method can produce assimilated global atmospheric data consistent with observations at 0. 25$^\circ$ ($\approx$30km) resolution globally. This marks the highest resolution achieved by ML data assimilation models. The experiments also show that the initial conditions assimilated from sparse observations (less than 0. 96% of gridded data) and 48-hour forecast can be used for forecast models with a loss of lead time of at most 24 hours compared to initial conditions from state-of-the-art data assimilation in ERA5. This enables the application of the method to real-world applications, such as creating reanalysis datasets with autoregressive data assimilation.

Details

AAAI Conference 2024 Conference Paper

Graph of Thoughts: Solving Elaborate Problems with Large Language Models

Maciej Besta
Nils Blach
Ales Kubicek
Robert Gerstenberger
Michal Podstawski
Lukas Gianinazzi
Joanna Gajda
Tomasz Lehmann

We introduce Graph of Thoughts (GoT): a framework that advances prompting capabilities in large language models (LLMs) beyond those offered by paradigms such as Chain-of-Thought or Tree of Thoughts (ToT). The key idea and primary advantage of GoT is the ability to model the information generated by an LLM as an arbitrary graph, where units of information ("LLM thoughts") are vertices, and edges correspond to dependencies between these vertices. This approach enables combining arbitrary LLM thoughts into synergistic outcomes, distilling the essence of whole networks of thoughts, or enhancing thoughts using feedback loops. We illustrate that GoT offers advantages over state of the art on different tasks, for example increasing the quality of sorting by 62% over ToT, while simultaneously reducing costs by >31%. We ensure that GoT is extensible with new thought transformations and thus can be used to spearhead new prompting schemes. This work brings the LLM reasoning closer to human thinking or brain mechanisms such as recurrence, both of which form complex networks

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs

Saleh Ashkboos
Amirkeivan Mohtashami
Maximilian L. Croci
Bo Li
Pashmina Cameron
Martin Jaggi
Dan Alistarh
Torsten Hoefler

We introduce QuaRot, a new Quantization scheme based on Rotations, which is able to quantize LLMs end-to-end, including all weights, activations, and KV cache in 4 bits. QuaRot rotates LLMs in a way that removes outliers from the hidden state without changing the output, making quantization easier. This computational invariance is applied to the hidden state (residual) of the LLM, as well as to the activations of the feed-forward components, aspects of the attention mechanism, and to the KV cache. The result is a quantized model where all matrix multiplications are performed in 4 bits, without any channels identified for retention in higher precision. Our 4-bit quantized LLAMA2-70B model has losses of at most 0. 47 WikiText-2 perplexity and retains 99% of the zero-shot performance. We also show that QuaRot can provide lossless 6 and 8 bit LLAMA-2 models without any calibration data using round-to-nearest quantization. Code is available at github. com/spcl/QuaRot.

PDF Details DOI

ICLR Conference 2024 Conference Paper

SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Saleh Ashkboos
Maximilian L. Croci
Marcelo Gennari Do Nascimento
Torsten Hoefler
James Hensman

Large language models have become the cornerstone of natural language processing, but their use comes with substantial costs in terms of compute and memory resources. Sparsification provides a solution to alleviate these resource constraints, and recent works have shown that trained models can be sparsified post-hoc. Existing sparsification techniques face challenges as they need additional data structures and offer constrained speedup with current hardware. In this paper we present SliceGPT, a new post-training sparsification scheme which replaces each weight matrix with a smaller (dense) matrix, reducing the embedding dimension of the network. Through extensive experimentation we show that SliceGPT can remove up to 25% of the model parameters (including embeddings) for LLAMA-2 70B, OPT 66B and Phi-2 models while maintaining 99%, 99% and 90% zero-shot task performance of the dense model respectively. Our sliced models run on fewer GPUs and run faster without any additional code optimization: on 24GB consumer GPUs we reduce the total compute for inference on LLAMA-2 70B to 64% of that of the dense model; on 40GB A100 GPUs we reduce it to 66%. We offer a new insight, computational invariance in transformer networks, which enables SliceGPT and we hope it will inspire and enable future avenues to reduce memory and computation demands for pre-trained models.

Details

ICLR Conference 2024 Conference Paper

SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

Tim Dettmers
Ruslan Svirschevski
Vage Egiazarian
Denis Kuznedelev
Elias Frantar
Saleh Ashkboos
Alexander Borzunov
Torsten Hoefler

Recent advances in large language model (LLM) pretraining have led to high-quality LLMs with impressive abilities. By compressing such LLMs via quantization to 3-4 bits per parameter, they can fit into memory-limited devices such as laptops and mobile phones, enabling personalized use. Quantizing models to 3-4 bits per parameter can lead to moderate to high accuracy losses, especially for smaller models (1-10B parameters), which are suitable for edge deployment. To address this accuracy issue, we introduce the Sparse-Quantized Representation (SpQR), a new compressed format and quantization technique that enables for the first time \emph{near-lossless} compression of LLMs across model scales while reaching similar compression levels to previous methods. SpQR works by identifying and isolating \emph{outlier weights}, which cause particularly large quantization errors, and storing them in higher precision while compressing all other weights to 3-4 bits, and achieves relative accuracy losses of less than $1\%$ in perplexity for highly-accurate LLaMA and Falcon LLMs. This makes it possible to run a 33B parameter LLM on a single 24 GB consumer GPU without performance degradation at 15\% speedup, thus making powerful LLMs available to consumers without any downsides. SpQR comes with efficient algorithms for both encoding weights into its format, as well as decoding them efficiently at runtime. Specifically, we provide an efficient GPU inference algorithm for SpQR, which yields faster inference than 16-bit baselines at similar accuracy while enabling memory compression gains of more than 4x.

Details

ICLR Conference 2023 Conference Paper

Compressing multidimensional weather and climate data into neural networks

Langwen Huang
Torsten Hoefler

Weather and climate simulations produce petabytes of high-resolution data that are later analyzed by researchers in order to understand climate change or severe weather. We propose a new method of compressing this multidimensional weather and climate data: a coordinate-based neural network is trained to overfit the data, and the resulting parameters are taken as a compact representation of the original grid-based data. While compression ratios range from 300x to more than 3,000x, our method outperforms the state-of-the-art compressor SZ3 in terms of weighted RMSE, MAE. It can faithfully preserve important large scale atmosphere structures and does not introduce significant artifacts. When using the resulting neural network as a 790x compressed dataloader to train the WeatherBench forecasting model, its RMSE increases by less than 2%. The three orders of magnitude compression democratizes access to high-resolution climate data and enables numerous new research directions.

Details

ICLR Conference 2023 Conference Paper

OPTQ: Accurate Quantization for Generative Pre-trained Transformers

Elias Frantar
Saleh Ashkboos
Torsten Hoefler
Dan Alistarh

Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart through breakthrough performance across complex language modelling tasks, but also by their extremely high computational and storage costs. Specifically, due to their massive size, even inference for large, highly-accurate GPT models may require multiple performant GPUs, which limits the usability of such models. While there is emerging work on relieving this pressure via model compression, the applicability and performance of existing compression techniques is limited by the scale and complexity of GPT models. In this paper, we address this challenge, and propose OPTQ, a new one-shot weight quantization method based on approximate second-order information, that is both highly-accurate and highly-efficient. Specifically, OPTQ can quantize GPT models with 175 billion parameters in approximately four GPU hours, reducing the bitwidth down to 3 or 4 bits per weight, with negligible accuracy degradation relative to the uncompressed baseline. Our method more than doubles the compression gains relative to previously-proposed one-shot quantization methods, preserving accuracy, allowing us for the first time to execute an 175 billion-parameter model inside a single GPU for generative inference. Moreover, we also show that our method can still provide reasonable accuracy in the extreme quantization regime, in which weights are quantized to 2-bit or even ternary quantization levels. We show experimentally that these improvements can be leveraged for end-to-end inference speedups over FP16, of around 3.25x when using high-end GPUs (NVIDIA A100) and 4.5x when using more cost-effective ones (NVIDIA A6000). The implementation is available at https://github.com/IST-DASLab/gptq.

Details

NeurIPS Conference 2022 Conference Paper

ENS-10: A Dataset For Post-Processing Ensemble Weather Forecasts

Saleh Ashkboos
Langwen Huang
Nikoli Dryden
Tal Ben-Nun
Peter Dueben
Lukas Gianinazzi
Luca Kummer
Torsten Hoefler

Post-processing ensemble prediction systems can improve the reliability of weather forecasting, especially for extreme event prediction. In recent years, different machine learning models have been developed to improve the quality of weather post-processing. However, these models require a comprehensive dataset of weather simulations to produce high-accuracy results, which comes at a high computational cost to generate. This paper introduces the ENS-10 dataset, consisting of ten ensemble members spanning 20 years (1998--2017). The ensemble members are generated by perturbing numerical weather simulations to capture the chaotic behavior of the Earth. To represent the three-dimensional state of the atmosphere, ENS-10 provides the most relevant atmospheric variables at 11 distinct pressure levels and the surface at \ang{0. 5} resolution for forecast lead times T=0, 24, and 48 hours (two data points per week). We propose the ENS-10 prediction correction task for improving the forecast quality at a 48-hour lead time through ensemble post-processing. We provide a set of baselines and compare their skill at correcting the predictions of three important atmospheric variables. Moreover, we measure the baselines' skill at improving predictions of extreme weather events using our dataset. The ENS-10 dataset is available under the Creative Commons Attribution 4. 0 International (CC BY 4. 0) license.

PDF Details

ICLR Conference 2022 Conference Paper

Neural Parameter Allocation Search

Bryan A. Plummer
Nikoli Dryden
Julius Frost
Torsten Hoefler
Kate Saenko

Training neural networks requires increasing amounts of memory. Parameter sharing can reduce memory and communication costs, but existing methods assume networks have many identical layers and utilize hand-crafted sharing strategies that fail to generalize. We introduce Neural Parameter Allocation Search (NPAS), a novel task where the goal is to train a neural network given an arbitrary, fixed parameter budget. NPAS covers both low-budget regimes, which produce compact networks, as well as a novel high-budget regime, where additional capacity can be added to boost performance without increasing inference FLOPs. To address NPAS, we introduce Shapeshifter Networks (SSNs), which automatically learn where and how to share parameters in a network to support any parameter budget without requiring any changes to the architecture or loss function. NPAS and SSNs provide a complete framework for addressing generalized parameter sharing, and can also be combined with prior work for additional performance gains. We demonstrate the effectiveness of our approach using nine network architectures across four diverse tasks, including ImageNet classification and transformers.

Details

NeurIPS Conference 2022 Conference Paper

Spatial Mixture-of-Experts

Nikoli Dryden
Torsten Hoefler

Many data have an underlying dependence on spatial location; it may be weather on the Earth, a simulation on a mesh, or a registered image. Yet this feature is rarely taken advantage of, and violates common assumptions made by many neural network layers, such as translation equivariance. Further, many works that do incorporate locality fail to capture fine-grained structure. To address this, we introduce the Spatial Mixture-of-Experts (SMoE) layer, a sparsely-gated layer that learns spatial structure in the input domain and routes experts at a fine-grained level to utilize it. We also develop new techniques to train SMoEs, including a self-supervised routing loss and damping expert errors. Finally, we show strong results for SMoEs on numerous tasks, and set new state-of-the-art results for medium-range weather prediction and post-processing ensemble weather forecasts.

PDF Details

ICML Conference 2021 Conference Paper

ProGraML: A Graph-based Program Representation for Data Flow Analysis and Compiler Optimizations

Chris Cummins
Zacharias V. Fisches
Tal Ben-Nun
Torsten Hoefler
Michael F. P. O'Boyle
Hugh James Leather

Machine learning (ML) is increasingly seen as a viable approach for building compiler optimization heuristics, but many ML methods cannot replicate even the simplest of the data flow analyses that are critical to making good optimization decisions. We posit that if ML cannot do that, then it is insufficiently able to reason about programs. We formulate data flow analyses as supervised learning tasks and introduce a large open dataset of programs and their corresponding labels from several analyses. We use this dataset to benchmark ML methods and show that they struggle on these fundamental program reasoning tasks. We propose ProGraML - Program Graphs for Machine Learning - a language-independent, portable representation of program semantics. ProGraML overcomes the limitations of prior works and yields improved performance on downstream optimization tasks.

Details

JMLR Journal 2021 Journal Article

Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks

Torsten Hoefler
Dan Alistarh
Tal Ben-Nun
Nikoli Dryden
Alexandra Peste

The growing energy and performance costs of deep learning have driven the community to reduce the size of neural networks by selectively pruning components. Similarly to their biological counterparts, sparse networks generalize just as well, sometimes even better than, the original dense networks. Sparsity promises to reduce the memory footprint of regular networks to fit mobile devices, as well as shorten training time for ever growing networks. In this paper, we survey prior work on sparsity in deep learning and provide an extensive tutorial of sparsification for both inference and training. We describe approaches to remove and add elements of neural networks, different training strategies to achieve model sparsity, and mechanisms to exploit sparsity in practice. Our work distills ideas from more than 300 research papers and provides guidance to practitioners who wish to utilize sparsity today, as well as to researchers whose goal is to push the frontier forward. We include the necessary background on mathematical methods in sparsification, describe phenomena such as early structure adaptation, the intricate relations between sparsity and the training process, and show techniques for achieving acceleration on real hardware. We also define a metric of pruned parameter efficiency that could serve as a baseline for comparison of different sparse networks. We close by speculating on how sparsity can improve future workloads and outline major open problems in the field. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2021. ( edit, beta )

PDF Details

NeurIPS Conference 2018 Conference Paper

Neural Code Comprehension: A Learnable Representation of Code Semantics

Tal Ben-Nun
Alice Shoshana Jakobovits
Torsten Hoefler

With the recent success of embeddings in natural language processing, research has been conducted into applying similar methods to code analysis. Most works attempt to process the code directly or use a syntactic tree representation, treating it like sentences written in a natural language. However, none of the existing methods are sufficient to comprehend program semantics robustly, due to structural features such as function calls, branching, and interchangeable order of statements. In this paper, we propose a novel processing technique to learn code semantics, and apply it to a variety of program analysis tasks. In particular, we stipulate that a robust distributional hypothesis of code applies to both human- and machine-generated programs. Following this hypothesis, we define an embedding space, inst2vec, based on an Intermediate Representation (IR) of the code that is independent of the source programming language. We provide a novel definition of contextual flow for this IR, leveraging both the underlying data- and control-flow of the program. We then analyze the embeddings qualitatively using analogies and clustering, and evaluate the learned representation on three different high-level tasks. We show that even without fine-tuning, a single RNN architecture and fixed inst2vec embeddings outperform specialized approaches for performance prediction (compute device mapping, optimal thread coarsening); and algorithm classification from raw code (104 classes), where we set a new state-of-the-art.

PDF Details

NeurIPS Conference 2018 Conference Paper

The Convergence of Sparsified Gradient Methods

Dan Alistarh
Torsten Hoefler
Mikael Johansson
Nikola Konstantinov
Sarit Khirirat
Cedric Renggli

Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace. Several families of communication-reduction methods, such as quantization, large-batch methods, and gradient sparsification, have been proposed. To date, gradient sparsification methods--where each node sorts gradients by magnitude, and only communicates a subset of the components, accumulating the rest locally--are known to yield some of the largest practical gains. Such methods can reduce the amount of communication per step by up to \emph{three orders of magnitude}, while preserving model accuracy. Yet, this family of methods currently has no theoretical justification. This is the question we address in this paper. We prove that, under analytic assumptions, sparsifying gradients by magnitude with local error correction provides convergence guarantees, for both convex and non-convex smooth objectives, for data-parallel SGD. The main insight is that sparsification methods implicitly maintain bounds on the maximum impact of stale updates, thanks to selection by magnitude. Our analysis and empirical validation also reveal that these methods do require analytical conditions to converge well, justifying existing heuristics.

PDF Details