Susan Wei

Aoqi Zuo, Susan Wei, Tongliang Liu et al.

Fair machine learning aims to avoid treating individuals or sub-populations unfavourably based on \textit{sensitive attributes}, such as gender and race. Those methods in fair machine learning that are built on causal inference ascertain discrimination and bias through causal effects. Though causality-based fair learning is attracting increasing attention, current methods assume the true causal graph is fully known. This paper proposes a general method to achieve the notion of counterfactual fairness when the true causal graph is unknown. To be able to select features that lead to counterfactual fairness, we derive the conditions and algorithms to identify ancestral relations between variables on a \textit{Partially Directed Acyclic Graph (PDAG)}, specifically, a class of causal DAGs that can be learned from observational data combined with domain knowledge. Interestingly, we find that counterfactual fairness can be achieved as if the true causal graph were fully known, when specific background knowledge is provided: the sensitive attributes do not have ancestors in the causal graph. Results on both simulated and real-world datasets demonstrate the effectiveness of our method.

Edmund Lau, Zach Furman, George Wang et al.

The Local Learning Coefficient (LLC) is introduced as a novel complexity measure for deep neural networks (DNNs). Recognizing the limitations of traditional complexity measures, the LLC leverages Singular Learning Theory (SLT), which has long recognized the significance of singularities in the loss landscape geometry. This paper provides an extensive exploration of the LLC's theoretical underpinnings, offering both a clear definition and intuitive insights into its application. Moreover, we propose a new scalable estimator for the LLC, which is then effectively applied across diverse architectures including deep linear networks up to 100M parameters, ResNet image models, and transformer language models. Empirical evidence suggests that the LLC provides valuable insights into how training heuristics might influence the effective complexity of DNNs. Ultimately, the LLC emerges as a crucial tool for reconciling the apparent contradiction between deep learning's complexity and the principle of parsimony.

Zhongtian Chen, Edmund Lau, Jake Mendel et al.

We investigate phase transitions in a Toy Model of Superposition (TMS) using Singular Learning Theory (SLT). We derive a closed formula for the theoretical loss and, in the case of two hidden dimensions, discover that regular $k$-gons are critical points. We present supporting theory indicating that the local learning coefficient (a geometric invariant) of these $k$-gons determines phase transitions in the Bayesian posterior as a function of training sample size. We then show empirically that the same $k$-gon critical points also determine the behavior of SGD training. The picture that emerges adds evidence to the conjecture that the SGD learning trajectory is subject to a sequential learning mechanism. Specifically, we find that the learning process in TMS, be it through SGD or Bayesian learning, can be characterized by a journey through parameter space from regions of high loss and low complexity to regions of low loss and high complexity.

Susan Wei, Edmund Lau

In this work, we advocate for the importance of singular learning theory (SLT) as it pertains to the theory and practice of variational inference in Bayesian neural networks (BNNs). To begin, using SLT, we lay to rest some of the confusion surrounding discrepancies between downstream predictive performance measured via e.g., the test log predictive density, and the variational objective. Next, we use the SLT-corrected asymptotic form for singular posterior distributions to inform the design of the variational family itself. Specifically, we build upon the idealized variational family introduced in \citet{bhattacharya_evidence_2020} which is theoretically appealing but practically intractable. Our proposal takes shape as a normalizing flow where the base distribution is a carefully-initialized generalized gamma. We conduct experiments comparing this to the canonical Gaussian base distribution and show improvements in terms of variational free energy and variational generalization error.

Sandra Fortini, Kenyon Ng, Sonia Petrone et al.

TabPFN is a transformer that achieves state-of-the-art performance on supervised tabular tasks by amortizing Bayesian prediction into a single forward pass. However, there is currently no method for uncertainty decomposition in TabPFN. Because it behaves, in an idealised limit, as a Bayesian in-context learner, we cast the decomposition challenge as a Bayesian predictive inference (BPI) problem. The main computational tool in BPI, predictive Monte Carlo, is challenging to apply here as it requires simulating unmodeled covariates. We therefore pursue the asymptotic alternative, filling a gap in the theory for supervised settings by proving a predictive CLT under quasi-martingale conditions. We derive variance estimators determined by the volatility of predictive updates along the context. The resulting credible bands are fast to compute, target epistemic uncertainty, and achieve near-nominal frequentist coverage. For classification, we further obtain an entropy-based uncertainty decomposition.

Jesse Hoogland, George Wang, Matthew Farrugia-Roberts et al.

Deep learning involves navigating a high-dimensional loss landscape over the neural network parameter space. Over the course of training, complex computational structures form and re-form inside the neural network, leading to shifts in input/output behavior. It is a priority for the science of deep learning to uncover principles governing the development of neural network structure and behavior. Drawing on the framework of singular learning theory, we propose that model development is deeply linked to degeneracy in the local geometry of the loss landscape. We investigate this link by monitoring loss landscape degeneracy throughout training, as quantified by the local learning coefficient, for a transformer language model and an in-context linear regression transformer. We show that training can be divided into distinct periods of change in loss landscape degeneracy, and that these changes in degeneracy coincide with significant changes in the internal computational structure and the input/output behavior of the transformers. This finding provides suggestive evidence that degeneracy and development are linked in transformers, underscoring the potential of a degeneracy-based perspective for understanding modern deep learning.

Simon Pepin Lehalleur, Jesse Hoogland, Matthew Farrugia-Roberts et al.

In this position paper, we argue that understanding the relation between structure in the data distribution and structure in trained models is central to AI alignment. First, we discuss how two neural networks can have equivalent performance on the training set but compute their outputs in essentially different ways and thus generalise differently. For this reason, standard testing and evaluation are insufficient for obtaining assurances of safety for widely deployed generally intelligent systems. We argue that to progress beyond evaluation to a robust mathematical science of AI alignment, we need to develop statistical foundations for an understanding of the relation between structure in the data distribution, internal structure in models, and how these structures underlie generalisation.

Aoqi Zuo, Yiqing Li, Susan Wei et al.

Fair machine learning aims to prevent discrimination against individuals or sub-populations based on sensitive attributes such as gender and race. In recent years, causal inference methods have been increasingly used in fair machine learning to measure unfairness by causal effects. However, current methods assume that the true causal graph is given, which is often not true in real-world applications. To address this limitation, this paper proposes a framework for achieving causal fairness based on the notion of interventions when the true causal graph is partially known. The proposed approach involves modeling fair prediction using a Partially Directed Acyclic Graph (PDAG), specifically, a class of causal DAGs that can be learned from observational data combined with domain knowledge. The PDAG is used to measure causal fairness, and a constrained optimization problem is formulated to balance between fairness and accuracy. Results on both simulated and real-world datasets demonstrate the effectiveness of this method.

Hui Li, Carlos A. Pena Solorzano, Susan Wei et al.

The ADMANI datasets (annotated digital mammograms and associated non-image datasets) from the Transforming Breast Cancer Screening with AI programme (BRAIx) run by BreastScreen Victoria in Australia are multi-centre, large scale, clinically curated, real-world databases. The datasets are expected to aid in the development of clinically relevant Artificial Intelligence (AI) algorithms for breast cancer detection, early diagnosis, and other applications. To ensure high data quality, technical outliers must be removed before any downstream algorithm development. As a first step, we randomly select 30,000 individual mammograms and use Convolutional Variational Autoencoder (CVAE), a deep generative neural network, to detect outliers. CVAE is expected to detect all sorts of outliers, although its detection performance differs among different types of outliers. Traditional image processing techniques such as erosion and pectoral muscle analysis can compensate for the poor performance of CVAE in certain outlier types. We identify seven types of technical outliers: implant, pacemaker, cardiac loop recorder, improper radiography, atypical lesion/calcification, incorrect exposure parameter and improper placement. The outlier recall rate for the test set is 61% if CVAE, erosion and pectoral muscle analysis each select the top 1% images ranked in ascending or descending order according to image outlier score under each detection method, and 83% if each selects the top 5% images. This study offers an overview of technical outliers in the ADMANI dataset and suggests future directions to improve outlier detection effectiveness.

Daniel Murfet, Susan Wei, Mingming Gong et al.

In singular models, the optimal set of parameters forms an analytic set with singularities and classical statistical inference cannot be applied to such models. This is significant for deep learning as neural networks are singular and thus "dividing" by the determinant of the Hessian or employing the Laplace approximation are not appropriate. Despite its potential for addressing fundamental issues in deep learning, singular learning theory appears to have made little inroads into the developing canon of deep learning theory. Via a mix of theory and experiment, we present an invitation to singular learning theory as a vehicle for understanding deep learning and suggest important future work to make singular learning theory directly applicable to how deep learning is performed in practice.

Susan Wei, Marc Niethammer

Algorithmic fairness seeks to identify and correct sources of bias in machine learning algorithms. Confoundingly, ensuring fairness often comes at the cost of accuracy. We provide formal tools in this work for reconciling this fundamental tension in algorithm fairness. Specifically, we put to use the concept of Pareto optimality from multi-objective optimization and seek the fairness-accuracy Pareto front of a neural network classifier. We demonstrate that many existing algorithmic fairness methods are performing the so-called linear scalarization scheme which has severe limitations in recovering Pareto optimal solutions. We instead apply the Chebyshev scalarization scheme which is provably superior theoretically and no more computationally burdensome at recovering Pareto optimal solutions compared to the linear scheme.

Nathaniel J. Bloomfield, Susan Wei, Bartholomew Woodham et al.

Biofouling is the accumulation of organisms on surfaces immersed in water. It is of particular concern to the international shipping industry because it increases fuel costs and presents a biosecurity risk by providing a pathway for non-indigenous marine species to establish in new areas. There is growing interest within jurisdictions to strengthen biofouling risk-management regulations, but it is expensive to conduct in-water inspections and assess the collected data to determine the biofouling state of vessel hulls. Machine learning is well suited to tackle the latter challenge, and here we apply deep learning to automate the classification of images from in-water inspections to identify the presence and severity of fouling. We combined several datasets to obtain over 10,000 images collected from in-water surveys which were annotated by a group biofouling experts. We compared the annotations from three experts on a 120-sample subset of these images, and found that they showed 89% agreement (95% CI: 87-92%). Subsequent labelling of the whole dataset by one of these experts achieved similar levels of agreement with this group of experts, which we defined as performing at most 5% worse (p=0.009-0.054). Using these expert labels, we were able to train a deep learning model that also agreed similarly with the group of experts (p=0.001-0.014), demonstrating that automated analysis of biofouling in images is feasible and effective using this method.

François-Xavier Vialard, Roland Kwitt, Susan Wei et al.

Continuous-depth neural networks can be viewed as deep limits of discrete neural networks whose dynamics resemble a discretization of an ordinary differential equation (ODE). Although important steps have been taken to realize the advantages of such continuous formulations, most current techniques are not truly continuous-depth as they assume \textit{identical} layers. Indeed, existing works throw into relief the myriad difficulties presented by an infinite-dimensional parameter space in learning a continuous-depth neural ODE. To this end, we introduce a shooting formulation which shifts the perspective from parameterizing a network layer-by-layer to parameterizing over optimal networks described only by a set of initial conditions. For scalability, we propose a novel particle-ensemble parametrization which fully specifies the optimal weight trajectory of the continuous-depth neural network. Our experiments show that our particle-ensemble shooting formulation can achieve competitive performance, especially on long-range forecasting tasks. Finally, though the current work is inspired by continuous-depth neural networks, the particle-ensemble shooting formulation also applies to discrete-time networks and may lead to a new fertile area of research in deep learning parametrization.