Author name cluster

Lars Kai Hansen

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.

35 papers

2 author rows

TMLR Journal 2026 Journal Article

BiSSL: Enhancing the Alignment Between Self-Supervised Pretraining and Downstream Fine-Tuning via Bilevel Optimization

Gustav Wagner Zakarias
Lars Kai Hansen
Zheng-Hua Tan

Models initialized from self-supervised pretraining may suffer from poor alignment with downstream tasks, limiting the extent to which subsequent fine-tuning can adapt relevant representations acquired during the pretraining phase. To mitigate this, we introduce BiSSL, a novel bilevel training framework that enhances the alignment of self-supervised pretrained models with downstream tasks by explicitly incorporating both the pretext and downstream tasks into a preparatory training stage prior to fine-tuning. BiSSL solves a bilevel optimization problem in which the lower-level adheres to the self-supervised pretext task, while the upper-level encourages the lower-level backbone to align with the downstream objective. The bilevel structure facilitates enhanced information sharing between the tasks, ultimately yielding a backbone model that is more aligned with the downstream task, providing a better initialization for subsequent fine-tuning. We propose a general training algorithm for BiSSL that is compatible with a broad range of pretext and downstream tasks. We demonstrate that our proposed framework significantly improves accuracy on the vast majority of a broad selection of image-domain downstream tasks, and that these gains are consistently retained across a wide range of experimental settings. In addition, exploratory alignment analyses further underpin that BiSSL enhances downstream alignment of pretrained representations.

PDF Details

NeurIPS Conference 2025 Conference Paper

Minimizing False-Positive Attributions in Explanations of Non-Linear Models

Anders Gjølbye
Stefan Haufe
Lars Kai Hansen

Suppressor variables can influence model predictions without being dependent on the target outcome, and they pose a significant challenge for Explainable AI (XAI) methods. These variables may cause false-positive feature attributions, undermining the utility of explanations. Although effective remedies exist for linear models, their extension to non-linear models and instance-based explanations has remained limited. We introduce PatternLocal, a novel XAI technique that addresses this gap. PatternLocal begins with a locally linear surrogate, e. g. , LIME, KernelSHAP, or gradient-based methods, and transforms the resulting discriminative model weights into a generative representation, thereby suppressing the influence of suppressor variables while preserving local fidelity. In extensive hyperparameter optimization on the XAI-TRIS benchmark, PatternLocal consistently outperformed other XAI methods and reduced false-positive attributions when explaining non-linear tasks, thereby enabling more reliable and actionable insights. We further evaluate PatternLocal on an EEG motor imagery dataset, demonstrating physiologically plausible explanations.

PDF Details

ICLR Conference 2024 Conference Paper

Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners

Sarthak Yadav
Sergios Theodoridis
Lars Kai Hansen
Zheng-Hua Tan

In this work, we propose a Multi-Window Masked Autoencoder (MW-MAE) fitted with a novel Multi-Window Multi-Head Attention (MW-MHA) module that facilitates the modelling of local-global interactions in every decoder transformer block through attention heads of several distinct local and global windows. Empirical results on ten downstream audio tasks show that MW-MAEs consistently outperform standard MAEs in overall performance and learn better general-purpose audio representations, along with demonstrating considerably better scaling characteristics. Investigating attention distances and entropies reveals that MW-MAE encoders learn heads with broader local and global attention. Analyzing attention head feature representations through Projection Weighted Canonical Correlation Analysis (PWCCA) shows that attention heads with the same window sizes across the decoder layers of the MW-MAE learn correlated feature representations which enables each block to independently capture local and global information, leading to a decoupled decoder feature hierarchy.

Details

UAI Conference 2023 Conference Paper

On the role of model uncertainties in Bayesian optimisation

Jonathan Foldager
Mikkel Jordahn
Lars Kai Hansen
Michael Riis Andersen

Bayesian Optimization (BO) is a popular method for black-box optimization, which relies on uncertainty as part of its decision-making process when deciding which experiment to perform next. However, not much work has addressed the effect of uncertainty on the performance of the BO algorithm and to what extent calibrated uncertainties improve the ability to find the global optimum. In this work, we provide an extensive study of the relationship between the BO performance (regret) and uncertainty calibration for popular surrogate models and acquisition functions, and compare them across both synthetic and real-world experiments. Our results show that Gaussian Processes, and more surprisingly, Deep Ensembles are strong surrogate models. Our results further show a positive association between calibration error and regret, but interestingly, this association disappears when we control for the type of surrogate model in the analysis. We also study the effect of recalibration and demonstrate that it generally does not lead to improved regret. Finally, we provide theoretical justification for why uncertainty calibration might be difficult to combine with BO due to the small sample sizes commonly used.

Details

ICML Conference 2019 Conference Paper

Phase transition in PCA with missing data: Reduced signal-to-noise ratio, not sample size!

Niels Bruun Ipsen
Lars Kai Hansen

How does missing data affect our ability to learn signal structures? It has been shown that learning signal structure in terms of principal components is dependent on the ratio of sample size and dimensionality and that a critical number of observations is needed before learning starts (Biehl and Mietzner, 1993). Here we generalize this analysis to include missing data. Probabilistic principal component analysis is regularly used for estimating signal structures in datasets with missing data. Our analytic result suggest that the effect of missing data is to effectively reduce signal-to-noise ratio rather than - as generally believed - to reduce sample size. The theory predicts a phase transition in the learning curves and this is indeed found both in simulation data and in real datasets.

Details

JMLR Journal 2017 Journal Article

Bayesian Inference for Spatio-temporal Spike-and-Slab Priors

Michael Riis Andersen
Aki Vehtari
Ole Winther
Lars Kai Hansen

In this work, we address the problem of solving a series of underdetermined linear inverse problemblems subject to a sparsity constraint. We generalize the spike-and-slab prior distribution to encode a priori correlation of the support of the solution in both space and time by imposing a transformed Gaussian process on the spike-and-slab probabilities. An expectation propagation (EP) algorithm for posterior inference under the proposed model is derived. For large scale problems, the standard EP algorithm can be prohibitively slow. We therefore introduce three different approximation schemes to reduce the computational complexity. Finally, we demonstrate the proposed model using numerical experiments based on both synthetic and real data sets. [abs] [ pdf ][ bib ] &copy JMLR 2017. ( edit, beta )

PDF Details

YNIMG Journal 2017 Journal Article

Spatio-temporal reconstruction of brain dynamics from EEG with a Markov prior

Sofie Therese Hansen
Lars Kai Hansen

Electroencephalography (EEG) can capture brain dynamics in high temporal resolution. By projecting the scalp EEG signal back to its origin in the brain also high spatial resolution can be achieved. Source localized EEG therefore has potential to be a very powerful tool for understanding the functional dynamics of the brain. Solving the inverse problem of EEG is however highly ill-posed as there are many more potential locations of the EEG generators than EEG measurement points. Several well-known properties of brain dynamics can be exploited to alleviate this problem. More short ranging connections exist in the brain than long ranging, arguing for spatially focal sources. Additionally, recent work (Delorme et al. , 2012) argues that EEG can be decomposed into components having sparse source distributions. On the temporal side both short and long term stationarity of brain activation are seen. We summarize these insights in an inverse solver, the so-called “Variational Garrote” (Kappen and Gómez, 2013). Using a Markov prior we can incorporate flexible degrees of temporal stationarity. Through spatial basis functions spatially smooth distributions are obtained. Sparsity of these are inherent to the Variational Garrote solver. We name our method the MarkoVG and demonstrate its ability to adapt to the temporal smoothness and spatial sparsity in simulated EEG data. Finally a benchmark EEG dataset is used to demonstrate MarkoVG's ability to recover non-stationary brain dynamics.