arXiv subjects

Sören Laue

Publications and source records attributed to Sören Laue.

16 recordsLinked to original sources

arXiv2026

A Structural Theory of Position Bias in Transformers

Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. This bias is closely connected to the Lost-in-the-Middle phenomenon, where models underutilize information placed in the middle of the context. We show that causal Transformer architectures induce a systematic position-bias prior that can help explain the influence profiles associated with Lost-in-the-Middle. To characterize this prior, we develop a structural theory based on cumulative attention rollout with layerwise residual mixing. At finite depth, we isolate the competing positional drifts induced by causal masking, residual mixing, and positional encoding. Their interaction produces broad, often U-shaped profiles. At infinite depth, prior work predicts inevitable collapse under attention-only theory and identifies the discrepancy with observed Transformer behavior as an open problem. Under the stated boundedness assumptions, our residual-aware analysis replaces inevitable collapse with a dichotomy governed by cumulative attention mixing. Empirically, across 30 model-dataset settings, our adaptive residual-aware rollout closely matches measured input-token influence and reduces the average profile discrepancy by approximately 85% relative to both the attention-only and fixed-residual rollout baselines.

cs.LG↗

arXiv2026

Compact Language, Complex Model Shifts: How and Where Ambiguity and Underspecification Affect LLMs

We analyze how lexical ambiguity and underspecification affect language model training. We create artificial homonyms and artificial hypernyms as pseudowords and analyze the generative performance of language models as they are trained with increasing amounts of these ambiguous or underspecified pseudoword types. We further analyze whether the models disambiguate ambiguous or underspecified statements and provide a first mechanistic account of how ambiguity and disambiguation are represented internally. Our main results show that both ambiguity and underspecification increase model performance in ways that scale with their influence on the language's type-token ratio. However, the accuracy of generating sequences containing ambiguous words or their synonyms decreases compared to other texts. We also show that internal representations of pseudowords reflect disambiguation of pseudo-homonyms, but underspecification of pseudo-hypernyms is maintained during the generative process.

cs.CL↗

arXiv2026

LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer Models

Large Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance remain unclear. Different methods for LLM explainability exist, and many are, as a method, not fully understood themselves. We started with the question of how linguistic abstraction emerges in LLMs, aiming to detect it across different LLM modules (attention heads and input embeddings). For this, we used methods well-established in the literature: (1) probing for token-level relational structures, and (2) feature-mapping using embeddings as carriers of human-interpretable properties. Both attempts failed for different methodological reasons: Attention-based explanations collapsed once we tested the core assumption that later-layer representations still correspond to tokens. Property-inference methods applied to embeddings also failed because their high predictive scores were driven by methodological artifacts and dataset structure rather than meaningful semantic knowledge. These failures matter because both techniques are widely treated as evidence for what LLMs supposedly understand, yet our results show such conclusions are unwarranted. These limitations are particularly relevant in pervasive and distributed computing settings where LLMs are deployed as system components and interpretability methods are relied upon for debugging, compression, and explaining models.

cs.CL↗

arXiv2025

Joint Design of Protein Surface and Structure Using a Diffusion Bridge Model

Protein-protein interactions (PPIs) are governed by surface complementarity and hydrophobic interactions at protein interfaces. However, designing diverse and physically realistic protein structure and surfaces that precisely complement target receptors remains a significant challenge in computational protein design. In this work, we introduce PepBridge, a novel framework for the joint design of protein surface and structure that seamlessly integrates receptor surface geometry and biochemical properties. Starting with a receptor surface represented as a 3D point cloud, PepBridge generates complete protein structures through a multi-step process. First, it employs denoising diffusion bridge models (DDBMs) to map receptor surfaces to ligand surfaces. Next, a multi-model diffusion model predicts the corresponding structure, while Shape-Frame Matching Networks ensure alignment between surface geometry and backbone architecture. This integrated approach facilitates surface complementarity, conformational stability, and chemical feasibility. Extensive validation across diverse protein design scenarios demonstrates PepBridge's efficacy in generating structurally viable proteins, representing a significant advancement in the joint design of top-down protein structure.

cs.LG↗

arXiv2025

Prediction is not Explanation: Revisiting the Explanatory Capacity of Mapping Embeddings

Understanding what knowledge is implicitly encoded in deep learning models is essential for improving the interpretability of AI systems. This paper examines common methods to explain the knowledge encoded in word embeddings, which are core elements of large language models (LLMs). These methods typically involve mapping embeddings onto collections of human-interpretable semantic features, known as feature norms. Prior work assumes that accurately predicting these semantic features from the word embeddings implies that the embeddings contain the corresponding knowledge. We challenge this assumption by demonstrating that prediction accuracy alone does not reliably indicate genuine feature-based interpretability. We show that these methods can successfully predict even random information, concluding that the results are predominantly determined by an algorithmic upper bound rather than meaningful semantic representation in the word embeddings. Consequently, comparisons between datasets based solely on prediction performance do not reliably indicate which dataset is better captured by the word embeddings. Our analysis illustrates that such mappings primarily reflect geometric similarity within vector spaces rather than indicating the genuine emergence of semantic properties.

cs.CL↗

arXiv2025

Information Preserving Line Search via Bayesian Optimization

Line search is a fundamental part of iterative optimization methods for unconstrained and bound-constrained optimization problems to determine suitable step lengths that provide sufficient improvement in each iteration. Traditional line search methods are based on iterative interval refinement, where valuable information about function value and gradient is discarded in each iteration. We propose a line search method via Bayesian optimization, preserving and utilizing otherwise discarded information to improve step-length choices. Our approach is guaranteed to converge and shows superior performance compared to state-of-the-art methods based on empirical tests on the challenging unconstrained and bound-constrained optimization problems from the CUTEst test set.

math.OC↗

arXiv2024

Efficient Line Search Method Based on Regression and Uncertainty Quantification

Unconstrained optimization problems are typically solved using iterative methods, which often depend on line search techniques to determine optimal step lengths in each iteration. This paper introduces a novel line search approach. Traditional line search methods, aimed at determining optimal step lengths, often discard valuable data from the search process and focus on refining step length intervals. This paper proposes a more efficient method using Bayesian optimization, which utilizes all available data points, i.e., function values and gradients, to guide the search towards a potential global minimum. This new approach more effectively explores the search space, leading to better solution quality. It is also easy to implement and integrate into existing frameworks. Tested on the challenging CUTEst test set, it demonstrates superior performance compared to existing state-of-the-art methods, solving more problems to optimality with equivalent resource usage.

math.OC↗

arXiv2024

Detecting Conceptual Abstraction in LLMs

We present a novel approach to detecting noun abstraction within a large language model (LLM). Starting from a psychologically motivated set of noun pairs in taxonomic relationships, we instantiate surface patterns indicating hypernymy and analyze the attention matrices produced by BERT. We compare the results to two sets of counterfactuals and show that we can detect hypernymy in the abstraction mechanism, which cannot solely be related to the distributional similarity of noun pairs. Our findings are a first step towards the explainability of conceptual abstraction in LLMs.

cs.CL↗

arXiv2023

Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption

Capsule neural networks replace simple, scalar-valued neurons with vector-valued capsules. They are motivated by the pattern recognition system in the human brain, where complex objects are decomposed into a hierarchy of simpler object parts. Such a hierarchy is referred to as a parse-tree. Conceptually, capsule neural networks have been defined to realize such parse-trees. The capsule neural network (CapsNet), by Sabour, Frosst, and Hinton, is the first actual implementation of the conceptual idea of capsule neural networks. CapsNets achieved state-of-the-art performance on simple image recognition tasks with fewer parameters and greater robustness to affine transformations than comparable approaches. This sparked extensive follow-up research. However, despite major efforts, no work was able to scale the CapsNet architecture to more reasonable-sized datasets. Here, we provide a reason for this failure and argue that it is most likely not possible to scale CapsNets beyond toy examples. In particular, we show that the concept of a parse-tree, the main idea behind capsule neuronal networks, is not present in CapsNets. We also show theoretically and experimentally that CapsNets suffer from a vanishing gradient problem that results in the starvation of many capsules during training.

cs.CV↗

arXiv2022

Convexity Certificates from Hessians

The Hessian of a differentiable convex function is positive semidefinite. Therefore, checking the Hessian of a given function is a natural approach to certify convexity. However, implementing this approach is not straightforward since it requires a representation of the Hessian that allows its analysis. Here, we implement this approach for a class of functions that is rich enough to support classical machine learning. For this class of functions, it was recently shown how to compute computational graphs of their Hessians. We show how to check these graphs for positive semidefiniteness. We compare our implementation of the Hessian approach with the well-established disciplined convex programming (DCP) approach and prove that the Hessian approach is at least as powerful as the DCP approach for differentiable functions. Furthermore, we show for a state-of-the-art implementation of the DCP approach that, for differentiable functions, the Hessian approach is actually more powerful. That is, it can certify the convexity of a larger class of differentiable functions.

math.OC↗

arXiv2022

Optimization for Classical Machine Learning Problems on the GPU

Constrained optimization problems arise frequently in classical machine learning. There exist frameworks addressing constrained optimization, for instance, CVXPY and GENO. However, in contrast to deep learning frameworks, GPU support is limited. Here, we extend the GENO framework to also solve constrained optimization problems on the GPU. The framework allows the user to specify constrained optimization problems in an easy-to-read modeling language. A solver is then automatically generated from this specification. When run on the GPU, the solver outperforms state-of-the-art approaches like CVXPY combined with a GPU-accelerated solver such as cuOSQP or SCS by a few orders of magnitude.

cs.LG↗

arXiv2020

A Simple and Efficient Tensor Calculus for Machine Learning

Computing derivatives of tensor expressions, also known as tensor calculus, is a fundamental task in machine learning. A key concern is the efficiency of evaluating the expressions and their derivatives that hinges on the representation of these expressions. Recently, an algorithm for computing higher order derivatives of tensor expressions like Jacobians or Hessians has been introduced that is a few orders of magnitude faster than previous state-of-the-art approaches. Unfortunately, the approach is based on Ricci notation and hence cannot be incorporated into automatic differentiation frameworks from deep learning like TensorFlow, PyTorch, autograd, or JAX that use the simpler Einstein notation. This leaves two options, to either change the underlying tensor representation in these frameworks or to develop a new, provably correct algorithm based on Einstein notation. Obviously, the first option is impractical. Hence, we pursue the second option. Here, we show that using Ricci notation is not necessary for an efficient tensor calculus and develop an equally efficient method for the simpler Einstein notation. It turns out that turning to Einstein notation enables further improvements that lead to even better efficiency. The methods that are described in this paper have been implemented in the online tool www.MatrixCalculus.org for computing derivatives of matrix and tensor expressions. An extended abstract of this paper appeared as "A Simple and Efficient Tensor Calculus", AAAI 2020.

cs.LG↗

arXiv2019

GENO -- GENeric Optimization for Classical Machine Learning

Although optimization is the longstanding algorithmic backbone of machine learning, new models still require the time-consuming implementation of new solvers. As a result, there are thousands of implementations of optimization algorithms for machine learning problems. A natural question is, if it is always necessary to implement a new solver, or if there is one algorithm that is sufficient for most models. Common belief suggests that such a one-algorithm-fits-all approach cannot work, because this algorithm cannot exploit model specific structure and thus cannot be efficient and robust on a wide variety of problems. Here, we challenge this common belief. We have designed and implemented the optimization framework GENO (GENeric Optimization) that combines a modeling language with a generic solver. GENO generates a solver from the declarative specification of an optimization problem class. The framework is flexible enough to encompass most of the classical machine learning problems. We show on a wide variety of classical but also some recently suggested problems that the automatically generated solvers are (1) as efficient as well-engineered specialized solvers, (2) more efficient by a decent margin than recent state-of-the-art solvers, and (3) orders of magnitude more efficient than classical modeling language plus solver approaches.

cs.LG↗

arXiv2018

Distributed Convex Optimization with Many Convex Constraints

We address the problem of solving convex optimization problems with many convex constraints in a distributed setting. Our approach is based on an extension of the alternating direction method of multipliers (ADMM) that recently gained a lot of attention in the Big Data context. Although it has been invented decades ago, ADMM so far can be applied only to unconstrained problems and problems with linear equality or inequality constraints. Our extension can handle arbitrary inequality constraints directly. It combines the ability of ADMM to solve convex optimization problems in a distributed setting with the ability of the Augmented Lagrangian method to solve constrained optimization problems, and as we show, it inherits the convergence guarantees of ADMM and the Augmented Lagrangian method.

math.OC↗

arXiv2016

Generating massive complex networks with hyperbolic geometry faster in practice

Generative network models play an important role in algorithm development, scaling studies, network analysis, and realistic system benchmarks for graph data sets. The commonly used graph-based benchmark model R-MAT has some drawbacks concerning realism and the scaling behavior of network properties. A complex network model gaining considerable popularity builds random hyperbolic graphs, generated by distributing points within a disk in the hyperbolic plane and then adding edges between points whose hyperbolic distance is below a threshold. We present in this paper a fast generation algorithm for such graphs. Our experiments show that our new generator achieves speedup factors of 3-60 over the best previous implementation. One billion edges can now be generated in under one minute on a shared-memory workstation. Furthermore, we present a dynamic extension to model gradual network change, while preserving at each step the point position probabilities.

cs.DS↗

arXiv2008

Geometric Set Cover and Hitting Sets for Polytopes in $R^3$

Suppose we are given a finite set of points $P$ in $\R^3$ and a collection of polytopes $\mathcal{T}$ that are all translates of the same polytope $T$. We consider two problems in this paper. The first is the set cover problem where we want to select a minimal number of polytopes from the collection $\mathcal{T}$ such that their union covers all input points $P$. The second problem that we consider is finding a hitting set for the set of polytopes $\mathcal{T}$, that is, we want to select a minimal number of points from the input points $P$ such that every given polytope is hit by at least one point. We give the first constant-factor approximation algorithms for both problems. We achieve this by providing an epsilon-net for translates of a polytope in $R^3$ of size $\bigO(\frac{1{ε)$.

cs.CG↗