papers

Publications (26)

cs.LG2019

PT-MMD: A Novel Statistical Framework for the Evaluation of Generative Systems

Alexander Potapov, Ian Colbert, Ken Kreutz-Delgado +2

Stochastic-sampling-based Generative Neural Networks, such as Restricted Boltzmann Machines and Generative Adversarial Networks, are now used for applications such as denoising, im…

cs.LG2026

Qronos: Correcting the Past by Shaping the Future... in Post-Training Quantization

Shihao Zhang, Haoyu Zhang, Ian Colbert +1

We introduce Qronos -- a new state-of-the-art post-training quantization algorithm that sequentially rounds and updates neural network weights. Qronos not only explicitly corrects…

cs.LG2026

Optimal Post-Training Quantization Scales and Where to Find Them

Juan Amboage, Pablo Monteagudo-Lago, Ian Colbert +2

Post-training quantization (PTQ) compresses large language models by mapping weights to low-bit representations. The scaling factor that defines the quantization grid is typically…

cs.LG2024

A2Q+: Improving Accumulator-Aware Weight Quantization

Ian Colbert, Alessandro Pappalardo, Jakoba Petri-Koenig +1

Quantization techniques commonly reduce the inference costs of neural networks by restricting the precision of weights and activations. Recent studies show that also reducing the p…

cs.LG2021

Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations

Xinyu Zhang, Ian Colbert, Ken Kreutz-Delgado +1

Quantization and pruning are core techniques used to reduce the inference costs of deep neural networks. State-of-the-art quantization techniques are currently applied to both the…

cs.AR2025

SIRA: Scaled-Integer Range Analysis for Optimizing FPGA Dataflow Neural Network Accelerators

Yaman Umuroglu, Christoph Berganski, Felix Jentzsch +8

While neural network quantization effectively reduces the cost of matrix multiplications, aggressive quantization can expose non-matrix-multiply operations as significant performan…

cs.LG2023

A2Q: Accumulator-Aware Quantization with Guaranteed Overflow Avoidance

Ian Colbert, Alessandro Pappalardo, Jakoba Petri-Koenig

We present accumulator-aware quantization (A2Q), a novel weight quantization method designed to train quantized neural networks (QNNs) to avoid overflow when using low-precision ac…

cs.DC2021

A Competitive Edge: Can FPGAs Beat GPUs at DCNN Inference Acceleration in Resource-Limited Edge Computing Applications?

Ian Colbert, Jake Daly, Ken Kreutz-Delgado +1

When trained as generative models, Deep Learning algorithms have shown exceptional performance on tasks involving high dimensional data such as image denoising and super-resolution…

cs.LG2026

Pushing the Limits of Block Rotations in Post-Training Quantization

Sai Sanjeet, Ian Colbert, Pablo Monteagudo-Lago +3

Recent post-training quantization (PTQ) methods have adopted block rotations to diffuse outliers prior to rounding. While this reduces the overhead of online full-vector rotations,…

cs.LG2025

Path Generation and Evaluation in Video Games: A Nonparametric Statistical Approach

Daniel Campa, Mehdi Saeedi, Ian Colbert +1

Navigation path traces play a crucial role in video game design, serving as a vital resource for both enhancing player engagement and fine-tuning non-playable character behavior. G…

cs.AR2026

DataGuard: Guaranteeing Private Training in Systolic-array Based Accelerators

Pawan Kumar Sanjaya, Christina Giannoula, Nikhil Shreekumar +6

Differential privacy (DP) and federated learning (FL) have emerged as important privacy-preserving approaches when using sensitive data to train machine learning (ML) models. FL en…

cs.CR2026

GPU Acceleration of Sparse Fully Homomorphic Encrypted DNNs

Lara D'Agata, Carlos Agulló-Domingo, Óscar Vera-López +7

Fully homomorphic encryption (FHE) has recently attracted significant attention as both a cryptographic primitive and a systems challenge. Given the latest advances in accelerated…

cs.LG2025

Improving Quantization with Post-Training Model Expansion

Giuseppe Franco, Pablo Monteagudo-Lago, Ian Colbert +2

The size of a model has been a strong predictor of its quality, as well as its cost. As such, the trade-off between model cost and quality has been well-studied. Post-training opti…

cs.AI2025

Combining Reinforcement Learning and Behavior Trees for NPCs in Video Games with AMD Schola

Tian Liu, Alex Cann, Ian Colbert +1

While the rapid advancements in the reinforcement learning (RL) research community have been remarkable, the adoption in commercial video games remains slow. In this paper, we outl…

cs.LG2026

Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos

Haoyu Zhang, Shihao Zhang, Ian Colbert +1

Post-training quantization (PTQ) has become a crucial tool for reducing the memory and compute costs of modern deep neural networks, including large language models (LLMs). Among P…

stat.ML2022

Human-Like Navigation Behavior: A Statistical Evaluation Framework

Ian Colbert, Mehdi Saeedi

Recent advancements in deep reinforcement learning have brought forth an impressive display of highly skilled artificial agents capable of complex intelligent behavior. In video ga…

cs.CV2021

An Energy-Efficient Edge Computing Paradigm for Convolution-based Image Upsampling

Ian Colbert, Ken Kreutz-Delgado, Srinjoy Das

A novel energy-efficient edge computing paradigm is proposed for real-time deep learning-based image upsampling applications. State-of-the-art deep learning solutions for image ups…

cs.CR2025

Exploiting Unstructured Sparsity in Fully Homomorphic Encrypted DNNs

Aidan Ferguson, Perry Gibson, Lara D'Agata +5

The deployment of deep neural networks (DNNs) in privacy-sensitive environments is constrained by computational overheads in fully homomorphic encryption (FHE). This paper explores…

cs.LG2022

Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversaries

Alexander Cann, Ian Colbert, Ihab Amer

The widespread adoption of deep neural networks in computer vision applications has brought forth a significant interest in adversarial robustness. Existing research has shown that…

eess.IV2019

AX-DBN: An Approximate Computing Framework for the Design of Low-Power Discriminative Deep Belief Networks

Ian Colbert, Ken Kreutz-Delgado, Srinjoy Das

The power budget for embedded hardware implementations of Deep Learning algorithms can be extremely tight. To address implementation challenges in such domains, new design paradigm…

cs.LG2021

Generative and Discriminative Deep Belief Network Classifiers: Comparisons Under an Approximate Computing Framework

Siqiao Ruan, Ian Colbert, Ken Kreutz-Delgado +1

The use of Deep Learning hardware algorithms for embedded applications is characterized by challenges such as constraints on device power consumption, availability of labeled data,…

cs.LG2026

Signed Symmetric Quantization for Few-Bit Integers

Ian Colbert, Eashan Dash, Pablo Monteagudo-Lago +5

The signed integer alphabet contains one more negative representable value than positive. Yet, by convention, the standard symmetric integer quantizer fixes its scale to be strictl…

cs.LG2023

Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance

Ian Colbert, Alessandro Pappalardo, Jakoba Petri-Koenig

We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We leverage weight no…

cs.LG2026

dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats

Giuseppe Franco, Ian Colbert, Pablo Monteagudo-Lago +2

The paper presents dMX, a differentiable framework that learns per-layer floating‑point bit‑widths for large language models, enabling mixed‑precision quantization that balances ac…

#mixed-precision quantization#floating-point formats#large language models#model compression
cs.LG2025

Accumulator-Aware Post-Training Quantization for Large Language Models

Ian Colbert, Giuseppe Franco, Fabian Grob +2

When quantizing weights and activations to increasingly narrower representations, the cost of additions begins to dominate that of multiplications in multiply-accumulate (MAC) unit…

cs.LG2021

Generating GPU Compiler Heuristics using Reinforcement Learning

Ian Colbert, Jake Daly, Norm Rubin

GPU compilers are complex software programs with many optimizations specific to target hardware. These optimizations are often controlled by heuristics hand-designed by compiler ex…