Christos Louizos — accepted AI-conference papers

2026

Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models

Julianna Piskorz, Cristina Pinneri, Alvaro Correia, Motasem Alfarra, Risheek Garrepalli, Christos Louizos

ICML 2026poster

Masked Diffusion Language Models (MDLMs) have recently emerged as a promising alternative to Autoregressive Language Models (ARLMs), leveraging a denoising objective that, in principle, should enable more uniform context utilisation. In this work, we examine the context comprehension abilities of MD…

Cited by 0 Source ↗Scholar ↗

2026

Search or Accelerate: Confidence-Switched Position Beam Search for Diffusion Language Models

Mingyu Cao, Alvaro Correia, Christos Louizos, Shiwei Liu, Lu Yin

ICML 2026poster

Diffusion Language Models (DLMs) generate text by iteratively denoising a masked sequence, repeatedly deciding which positions to commit at each step. Standard decoding follows a greedy rule, unmasking the most confident positions, yet this local choice can lock the model into a suboptimal unmasking…

Cited by 0 Source ↗Scholar ↗

2025

Approximating Full Conformal Prediction for Neural Network Regression with Gauss-Newton Influence

Dharmesh Tailor, Alvaro Correia, Eric Nalisnick, Christos Louizos

ICLR 2025poster

Uncertainty quantification is an important prerequisite for the deployment of deep learning models in safety-critical areas. Yet, this hinges on the uncertainty estimates being useful to the extent the prediction intervals are well-calibrated and sharp. In the absence of inherent uncertainty estimat…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits

Ashish J Khisti, MohammadReza Ebrahimi, Hassan Dbouk, Arash Behboodi, Roland Memisevic, Christos Louizos

ICLR 2025spotlight

We consider multi-draft speculative sampling, where the proposal sequences are sampled independently from different draft models. At each step, a token-level draft selection scheme takes a list of valid tokens as input and produces an output token whose distribution matches that of the target mode…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Non-exchangeable Conformal Prediction with Optimal Transport: Tackling Distribution Shift with Unlabeled Data

Alvaro Correia, Christos Louizos

NeurIPS 2025poster

Conformal prediction is a distribution-free uncertainty quantification method that has gained popularity in the machine learning community due to its finite-sample guarantees and ease of use. Its most common variant, dubbed split conformal prediction, is also computationally efficient as it boils do…

Cited by 0 Source ↗Scholar ↗

2024

A Mutual Information Perspective on Federated Contrastive Learning

Christos Louizos, Matthias Reisser, Denis Korzhenkov

ICLR 2024spotlight

We investigate contrastive learning in the federated setting through the lens of Sim- CLR and multi-view mutual information maximization. In doing so, we uncover a connection between contrastive representation learning and user verification; by adding a user verification loss to each client’s local…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

An Information Theoretic Perspective on Conformal Prediction

Alvaro Correia, Fabio Valerio Massoli, Christos Louizos, Arash Behboodi

NeurIPS 2024poster

Conformal Prediction (CP) is a distribution-free uncertainty estimation framework that constructs prediction sets guaranteed to contain the true answer with a user-specified probability. Intuitively, the size of the prediction set encodes a general notion of uncertainty, with larger sets associated…

Cited by 23 Source ↗PDF ↗Scholar ↗

2024

Importance Matching Lemma for Lossy Compression with Side Information

Buu Phan, Ashish Khisti, Christos Louizos

AISTATS 2024poster

We propose two extensions to existing importance sampling based methods for lossy compression. First, we introduce an importance sampling based compression scheme that is a variant of ordered random coding (Theis and Ahmed, 2022) and is amenable to direct evaluation of the achievable compression rat…

Cited by 7 Source ↗PDF ↗Scholar ↗

2024

On Sampling Strategies for Spectral Model Sharding

Denis Korzhenkov, Christos Louizos

NeurIPS 2024poster

The problem of heterogeneous clients in federated learning has recently drawn a lot of attention. Spectral model sharding, i.e., partitioning the model parameters into low-rank matrices based on the singular value decomposition, has been one of the proposed solutions for more efficient on-device tra…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Protect Your Score: Contact-Tracing with Differential Privacy Guarantees

Rob Romijnders, Christos Louizos, Yuki M. Asano, Max Welling

AAAI 2024technical

The pandemic in 2020 and 2021 had enormous economic and societal consequences, and studies show that contact tracing algorithms can be key in the early containment of the virus. While large strides have been made towards more effective contact tracing algorithms, we argue that privacy concerns curre…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2023

Hyperparameter Optimization through Neural Network Partitioning

Bruno Kacper Mlodozeniec, Matthias Reisser, Christos Louizos

ICLR 2023poster

Well-tuned hyperparameters are crucial for obtaining good generalization behavior in neural networks. They can enforce appropriate inductive biases, regularize the model and improve performance --- especially in the presence of limited data. In this work, we propose a simple and efficient way for op…

Cited by 6 Source ↗PDF ↗Scholar ↗

2023

No time to waste: practical statistical contact tracing with few low-bit messages

Rob Romijnders, Yuki M. Asano, Christos Louizos, Max Welling

AISTATS 2023poster

Pandemics have a major impact on society and the economy. In the case of a new virus, such as COVID-19, high-grade tests and vaccines might be slow to develop and scarce in the crucial initial phase. With no time to waste and lock-downs being expensive, contact tracing is thus an essential tool for…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2021

Federated Learning of User Verification Models Without Sharing Embeddings

Hossein Hosseini, Hyunsin Park, Sungrack Yun, Christos Louizos, Joseph Soriaga, Max Welling

ICML 2021spotlight

We consider the problem of training User Verification (UV) models in federated setup, where each user has access to the data of only one class and user embeddings cannot be shared with the server or other users. To address this problem, we propose Federated User Verification (FedUV), a framework in…

Cited by 31 Source ↗PDF ↗Scholar ↗

2020

Bayesian Bits: Unifying Quantization and Pruning

Mart van Baalen, Christos Louizos, Markus Nagel, Rana Ali Amjad, Ying Wang, Tijmen Blankevoort +1

NeurIPS 2020poster

We introduce Bayesian Bits, a practical method for joint mixed precision quantization and pruning through gradient based optimization. Bayesian Bits employs a novel decomposition of the quantization operation, which sequentially considers doubling the bit width. At each new bit width, the residual e…

Cited by 156 Source ↗PDF ↗Scholar ↗

2020

Gradient $\ell_1$ Regularization for Quantization Robustness

Milad Alizadeh, Arash Behboodi, Mart van Baalen, Christos Louizos, Tijmen Blankevoort, Max Welling

ICLR 2020poster

We analyze the effect of quantizing weights and activations of neural networks on their loss and derive a simple regularization scheme that improves robustness against post-training quantization. By training quantization-ready networks, our approach enables storing a single set of weights that can b…

Cited by 66 Source ↗Scholar ↗

2020

Up or Down? Adaptive Rounding for Post-Training Quantization

Markus Nagel, Rana Ali Amjad, Mart Van Baalen, Christos Louizos, Tijmen Blankevoort

ICML 2020poster

When quantizing neural networks, assigning each floating-point weight to its nearest fixed-point value is the predominant approach. We find that, perhaps surprisingly, this is not the best we can do. In this paper, we propose AdaRound, a better weight-rounding mechanism for post-training quantizatio…

Cited by 685 Source ↗PDF ↗Scholar ↗

2019

Relaxed Quantization for Discretized Neural Networks

Christos Louizos, Matthias Reisser, Tijmen Blankevoort, Efstratios Gavves, Max Welling

ICLR 2019poster

Neural network quantization has become an important research area due to its great impact on deployment of large models on resource constrained devices. In order to train networks that can be effectively discretized without loss of performance, we introduce a differentiable quantization procedure. D…

Cited by 224 Source ↗PDF ↗Scholar ↗

2019

The Functional Neural Process

Christos Louizos, Xiahan Shi, Klamer Schutte, Max Welling

NeurIPS 2019poster

We present a new family of exchangeable stochastic processes, the Functional Neural Processes (FNPs). FNPs model distributions over functions by learning a graph of dependencies on top of latent representations of the points in the given dataset. In doing so, they define a Bayesian model without exp…

Cited by 86 Source ↗PDF ↗code ↗Scholar ↗

2018

Learning Sparse Neural Networks through L_0 Regularization

Christos Louizos, Max Welling, Diederik P. Kingma

ICLR 2018poster

We propose a practical method for $L_0$ norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularization is interesting since (1) it can greatly speed up training and inference, and (2) it can improve generalization. AIC…

Cited by 1418 Source ↗PDF ↗code ↗Scholar ↗

2017

Bayesian Compression for Deep Learning

Christos Louizos, Karen Ullrich, Max Welling

NeurIPS 2017poster

Compression and computational efficiency in deep learning have become a problem of great significance. In this work, we argue that the most principled and effective way to attack this problem is by adopting a Bayesian point of view, where through sparsity inducing priors we prune large parts of the…

Cited by 604 Source ↗PDF ↗code ↗Scholar ↗

2017

Causal Effect Inference with Deep Latent-Variable Models

Christos Louizos, Uri Shalit, Joris M. Mooij, David Sontag, Richard Zemel, Max Welling

NeurIPS 2017poster

Learning individual-level causal effects from observational data, such as inferring the most effective medication for a specific patient, is a problem of growing importance for policy makers. The most important aspect of inferring causal effects from observational data is the handling of confounders…

Cited by 972 Source ↗PDF ↗Scholar ↗

2017

Multiplicative Normalizing Flows for Variational Bayesian Neural Networks

Christos Louizos, Max Welling

ICML 2017poster

We reinterpret multiplicative noise in neural networks as auxiliary random variables that augment the approximate posterior in a variational setting for Bayesian neural networks. We show that through this interpretation it is both efficient and straightforward to improve the approximation by employi…

Cited by 593 Source ↗PDF ↗Scholar ↗

2016

Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriors

Christos Louizos, Max Welling

ICML 2016poster

We introduce a variational Bayesian neural network where the parameters are governed via a probability distribution on random matrices. Specifically, we employ a matrix variate Gaussian (Gupta & Nagar ’99) parameter posterior distribution where we explicitly model the covariance among the input and…

Cited by 330 Source ↗PDF ↗Scholar ↗