Papers for

machine learning model builders

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Loss-based training can fail to enforce fair AI reward principles

Enforcing Axioms for AI Alignment under Loss-Based Rules

Abstract: Many alignment methods, most notably reinforcement learning from human feedback (RLHF), train reward models by minimizing a loss on pairwise comparisons of model responses. Inspired by principle-guided methods such as Constitutional AI, we treat each principle as a voter that compares responses according to that principle, for example, preferring the more helpful or less toxic response. We represent these voters as linear directions in a fixed embedding space, a simplifying assumption motivated by the Linear Representation Hypothesis. In this linear social choice model, Ge et al. (2024) showed that an optimal linear reward model can violate Pareto optimality (PO): From the principles-as-voters lens, this means a response A can be less helpful and more toxic than B, yet still receive a higher reward. We ask whether richer reward models or changes to comparison data can recover PO within loss-based training. We show that PO can still fail for polynomials of any fixed degree and one-hidden-layer ReLU multilayer perceptrons (MLPs) of any fixed width $ d\ge 2 $ with suitable finite parameter bounds. We then recover PO for loss-based training of linear rewards under suitable assumptions in an idealized setting with uniform comparison directions and equal comparison lengths. These results motivate dataset design as an approach to recovering PO in constitutional-style alignment while retaining loss-based training.

Mon 9 NovComputer Science and Game TheoryArtificial IntelligenceMachine Learning
The gist
Many AI systems learn what to do by comparing pairs of responses and deciding which is better. This paper looks at how to make sure these systems always pick responses that are better according to common principles, like being helpful and not toxic. The authors find that even if AI uses more complex models, it can still make choices that don't match these principles perfectly. However, by carefully designing the comparison data the AI learns from, it's possible to make sure it follows all these principles correctly in ideal cases.
Open → 2611.13369v1

Locally adaptive intervals improve uncertainty estimates for polynomial models

Locally Adaptive Conformal Prediction for Polynomial Chaos Expansions

Abstract: This work develops a locally adaptive jackknife+ conformal prediction framework for polynomial chaos expansions. Therein, the non-conformity scores are normalized with an auxiliary polynomial chaos expansion trained on the log-transformed leave-one-out residuals of the base model. We show that the coverage guarantee of jackknife+ conformal prediction carries over to the adaptive intervals if the leave-one-out auxiliary models are trained on nested leave-one-out residuals. For fixed-basis polynomial chaos expansions fitted by ordinary least squares, all required quantities are derived in closed form and the guarantee-preserving adaptive intervals are obtained from a single model fit, without any model retraining. For sparse polynomial chaos expansions, where multiple model fits are necessary, we propose a heuristic simplification that limits the computational overhead of adaptivity at the cost of the formal coverage guarantee. Numerical experiments on an academic benchmark with known heteroscedastic noise and on an engineering simulation dataset show that the suggested method attains the target coverage while providing intervals that adapt to local prediction uncertainty, therefore being considerably more statistically efficient. These advantages are particularly prominent in high-uncertainty regions of the input space, where the performance of non-adaptive methods degrades substantially.

Fri 6 NovComputational Engineering, Finance, and Science
The gist
Making predictions sometimes involves uncertainty, and understanding how confident to be is important. The authors developed a method to better measure uncertainty in polynomial models by adjusting prediction intervals based on local data behavior. Their approach ensures reliable error bounds while adapting to areas where predictions are less certain. Testing shows it works well especially where traditional methods struggle with varying noise levels.
Open → 2611.09579v1

Bayesian interpretation unifies classical optimal design criteria in statistics

A Bayesian-Geometric Reading of Classical Model-Based Optimal Design

Abstract: The classical model-based optimal design criteria (D-, T-, L-, C-, and A-optimality) are usually motivated via the Cramér--Rao bound as optimizing scalar functions of the Fisher information matrix (FIM). This paper offers a complementary reading in which each criterion appears asymptotically as $N \to \infty$ as the leading-order term of an expected dissimilarity between prior and posterior, with the FIM entering through the Bernstein--von Mises limit. The Kullback--Leibler (KL) divergence of the posterior relative to the prior recovers D-optimality (classically known); a reverse KL of the prior relative to the posterior recovers T-optimality (here defined as maximization of the trace of the FIM, following one common convention) and its weighted-trace generalization; and a first-order approximation of the squared 2-Wasserstein distance recovers L-, C- and A-optimality. The five criteria emerge as instances of a common Bayesian-geometric template, indexed by three choices: the dissimilarity, the prior parametrization, and the approximation scheme used to evaluate it (e.g.\ Taylor expansions of the matrix square root). For the weighted criteria, the Gaussian prior covariance encodes the criterion's weight matrix, so any choice of weights corresponds to a specific prior in the family. The T-, L-, C-, and A-optimality derivations appear novel to the best of my knowledge. A sixth criterion, E-optimality, is recovered not as an independent expected-dissimilarity limit but as a min-max robustification of C-optimality against uncertainty in the modeler's prior direction. The framework is extended to distinguish between a designer's prior over unknown parameters at design time and a modeler's prior used for posterior inference, recovering the classical expected information gain objective as a special case.

Tue 3 NovInformation Theory
The gist
Designing experiments often involves choosing the best way to gather information about unknown things. This paper shows that many classical methods for choosing designs can all be seen as measuring how much our knowledge improves, in a Bayesian sense, after we see new data. By connecting these methods to mathematical distances between what we thought before and what we believe after the experiment, the authors offer a new viewpoint that unites different approaches. This helps explain why these methods work and how they relate to each other under a common framework.
Open → 2611.04450v1

Diffusion transformers denoise images using adaptive patch-based rules

How Do DiTs Denoise? An Aggregator-Predictor View of Attention and MLPs

Abstract: How do diffusion transformers (DiTs) represent image content and learn rules for reusing it to generalize? We develop an aggregator--predictor view of DiTs as input-adaptive local denoisers, in which context aggregation and patch prediction provide functional roles for interpreting attention and MLPs. We first establish that, for Gaussian Markov random field (GMRF) priors, the global Bayes denoiser can be approximated using only a subset of context patches, with error decaying exponentially in context radius. We further show that patchwise linear denoisers, often invoked to explain diffusion generalization, recover the empirical local denoiser with sufficiently informative aggregation. Within this view, AdaLN-modulated attention naturally parameterizes an input- and noise-dependent aggregator, while the MLP admits a learned key--value representation for tokenwise patch prediction. Our experiments support this view. DiTs trained on real images exhibit noise-dependent denoising contexts resembling those in the analytic GMRF setting, while attention mass exhibits a qualitatively corresponding broadening pattern. In a controlled CelebA64 study, shared-memory patch predictors used in place of DiT MLPs achieve competitive denoising and generative performance. Finally, cross-dataset component transplantation reveals compatibility patterns consistent with the proposed roles of QK in spatial weighting, VO in feature transport, and MLPs in patch prediction. Together, these results provide a component-level account of DiT denoising and motivate architecture-specific fine-tuning and controlled intervention.

Wed 21 OctComputer Vision and Pattern Recognition
The gist
This paper investigates how diffusion transformers clean up noisy images. It shows that these models work by looking at small image patches and predicting clean versions based on their surrounding context. The authors explain that attention helps the model decide which parts of the image to focus on, while other parts generate the actual predictions. Their experiments with real and synthetic images support this understanding and show how their findings can improve model design.
Open → 2610.29854v1

Topology optimization automatically tunes design hyperparameters during optimization

Bilevel Optimization of Topology and Hyperparameters (BOTH)

Abstract: Topology optimization (TO) represents a significant step towards automating the design process: given a working simulation, TO can produce a viable prototype at the press of a button by differentiating the simulation and iteratively improving the design. In practice, however, TO is riddled with ``magic numbers''---hyperparameters whose tuning significantly affects the outcome. Finding the right values typically requires not only deep problem-specific knowledge but also extensive trial-and-error. While practitioners can use surrogate-assisted hyperparameter optimization as an alternative, this approach requires strictly limiting the number of hyperparameters through careful problem formulation. Here, we propose differentiating TO itself using automatic differentiation. This yields ``hypergradients'' that allow us to tune these hyperparameters in tandem with the primary optimization. We show that evaluating just one or two steps of TO is sufficiently informative and that the method scales favorably to thousands of hyperparameters at an expense comparable to only a few standard TO runs. We demonstrate this approach on stress-constrained and compliance problems, with the latter utilizing a neural parameterization of the density field.

Fri 18 SeptMachine Learning
The gist
Designing objects often involves picking settings called hyperparameters, which are usually hard to choose and need lots of trial and error. The authors show how to automatically adjust these settings while designing, by calculating how small changes affect the design quality. This approach uses information from just a few optimization steps and can handle many hyperparameters efficiently. It helps create better designs by tuning settings alongside the main design process without extra guesswork.
Open → 2609.21758v1