To Give or Not to Give? The Impacts of Strategically Withheld Recourse Yatong Chen Andrew Estornell MPI for Intelligent Systems, T ubingen AI Center, T ubingen, Germany Bytedance Research Yevgeniy Vorobeychik Yang Liu Washington University in Saint Louis University of California, Santa Cruz Abstract Individuals often aim to reverse undesired outcomes in interactions with automated systems, like loan denials, by either implementing system-recommended actions (recourse), or manipulating their features. While providing recourse benefits users and enhances system utility, it also provides information about the decision process that can be used for more effective strategic manipulation, especially when the individuals collectively share such information with each other. We show that this tension leads rational utility-maximizing systems to frequently withhold recourse, resulting in decreased population utility, particularly impacting sensitive groups. To mitigate these effects, we explore ...

Survival Regression (SuR) is a key technique for modeling time to event in important applications such as clinical trials and semiconductor manufacturing. Currently, SuR algorithms belong to one of three classes: non-linear black-box -- allowing adaptability to many datasets but offering limited interpretability (e.g., tree ensembles); linear glass-box -- being easier to interpret but limited to modeling only linear interactions (e.g., Cox proportional hazards); and non-linear glass-box -- allowing adaptability and interpretability, but empirically found to have several limitations (e.g., explainable boosting machines, survival trees). In this work, we investigate whether Symbolic Regression (SR), i.e., the automated search of mathematical expressions from data, can lead to non-linear glass-box survival models that are interpretable and accurate. We propose an evolutionary, multi-objective, and multi-expression implementation of SR adapted to SuR. Our empirical results on five real-world datasets show that SR consistently outperforms traditional glass-box methods for SuR in terms of accuracy per number of dimensions in the model, while exhibiting comparable accuracy with black-box methods. Furthermore, we offer qualitative examples to assess the interpretability potential of SR models for SuR. Code at: https://github.com/lurovi/SurvivalMultiTree-pyNSGP.

This paper presents a comprehensive review of AI-driven prognostics for State of Health (SoH) prediction in lithium-ion batteries. We compare the effectiveness of various AI algorithms, including FFNN, LSTM, and BiLSTM, across multiple datasets (CALCE, NASA, UDDS) and scenarios (e.g., varying temperatures and driving conditions). Additionally, we analyze the factors influencing SoH fluctuations, such as temperature and charge-discharge rates, and validate our findings through simulations. The results demonstrate that BiLSTM achieves the highest accuracy, with an average RMSE reduction of 15% compared to LSTM, highlighting its robustness in real-world applications.

Differential privacy (DP) has become a prevalent privacy model in a wide range of machine learning tasks, especially after the debut of DP-SGD. However, DP-SGD, which directly perturbs gradients in the training iterations, fails to mitigate the negative impacts of noise on gradient direction. As a result, DP-SGD is often inefficient. Although various solutions (e.g., clipping to reduce the sensitivity of gradients and amplifying privacy bounds to save privacy budgets) are proposed to trade privacy for model efficiency, the root cause of its inefficiency is yet unveiled. In this work, we first generalize DP-SGD and theoretically derive the impact of DP noise on the training process. Our analysis reveals that, in terms of a perturbed gradient, only the noise on direction has eminent impact on the model efficiency while that on magnitude can be mitigated by optimization techniques, i.e., fine-tuning gradient clipping and learning rate. Besides, we confirm that traditional DP introduces biased noise on the direction when adding unbiased noise to the gradient itself. Overall, the perturbation of DP-SGD is actually sub-optimal from a geometric perspective. Motivated by this, we design a geometric perturbation strategy GeoDP within the DP framework, which perturbs the direction and the magnitude of a gradient, respectively. By directly reducing the noise on the direction, GeoDP mitigates the negative impact of DP noise on model efficiency with the same DP guarantee. Extensive experiments on two public datasets (i.e., MNIST and CIFAR-10), one synthetic dataset and three prevalent models (i.e., Logistic Regression, CNN and ResNet) confirm the effectiveness and generality of our strategy.

Predicting external hand load from sensor data is essential for ergonomic exposure assessments, as obtaining this information typically requires direct observation or supplementary data. While machine learning methods have been used to estimate external hand load from worker postures or force exertion data, our findings reveal systematic bias in these predictions due to individual differences such as age and biological sex. To explore this issue, we examined bias in hand load prediction by varying the sex ratio in the training dataset. We found substantial sex disparity in predictive performance, especially when the training dataset is more sex-imbalanced. To address this bias, we developed and evaluated a fair predictive model for hand load estimation that leverages a Variational Autoencoder (VAE) with feature disentanglement. This approach is designed to separate sex-agnostic and sex-specific latent features, minimizing feature overlap. The disentanglement capability enables the model to make predictions based solely on sex-agnostic features of motion patterns, ensuring fair prediction for both biological sexes. Our proposed fair algorithm outperformed conventional machine learning methods (e.g., Random Forests) in both fairness and predictive accuracy, achieving a lower mean absolute error (MAE) difference across male and female sets and improved fairness metrics such as statistical parity (SP) and positive and negative residual differences (PRD and NRD), even when trained on imbalanced sex datasets. These findings emphasize the importance of fairness-aware machine learning algorithms to prevent potential disadvantages in workplace health and safety for certain worker populations.

We introduce SoundVista, a method to generate the ambient sound of an arbitrary scene at novel viewpoints. Given a pre-acquired recording of the scene from sparsely distributed microphones, SoundVista can synthesize the sound of that scene from an unseen target viewpoint. The method learns the underlying acoustic transfer function that relates the signals acquired at the distributed microphones to the signal at the target viewpoint, using a limited number of known recordings. Unlike existing works, our method does not require constraints or prior knowledge of sound source details. Moreover, our method efficiently adapts to diverse room layouts, reference microphone configurations and unseen environments. To enable this, we introduce a visual-acoustic binding module that learns visual embeddings linked with local acoustic properties from panoramic RGB and depth data. We first leverage these embeddings to optimize the placement of reference microphones in any given scene. During synthesis, we leverage multiple embeddings extracted from reference locations to get adaptive weights for their contribution, conditioned on target viewpoint. We benchmark the task on both publicly available data and real-world settings. We demonstrate significant improvements over existing methods.

Nearest neighbour search over dense vector collections has important applications in information retrieval, retrieval augmented generation (RAG), and content ranking. Performing efficient search over large vector collections is a well studied problem with many existing approaches and open source implementations. However, most state-of-the-art systems are generally targeted towards scenarios using large servers with an abundance of memory, static vector collections that are not updatable, and nearest neighbour search in isolation of other search criteria. We present Micro Nearest Neighbour (MicroNN), an embedded nearest-neighbour vector search engine designed for scalable similarity search in low-resource environments. MicroNN addresses the problem of on-device vector search for real-world workloads containing updates and hybrid search queries that combine nearest neighbour search with structured attribute filters. In this scenario, memory is highly constrained and disk-efficient index structures and algorithms are required, as well as support for continuous inserts and deletes. MicroNN is an embeddable library that can scale to large vector collections with minimal resources. MicroNN is used in production and powers a wide range of vector search use-cases on-device. MicroNN takes less than 7 ms to retrieve the top-100 nearest neighbours with 90% recall on publicly available million-scale vector benchmark while using ~10 MB of memory.

Deep classifiers are known to be sensitive to data distribution shifts, primarily due to their reliance on spurious correlations in training data. It has been suggested that these classifiers can still find useful features in the network's last layer that hold up under such shifts. In this work, we question the use of last-layer representations for out-of-distribution (OOD) generalisation and explore the utility of intermediate layers. To this end, we introduce \textit{Intermediate Layer Classifiers} (ILCs). We discover that intermediate layer representations frequently offer substantially better generalisation than those from the penultimate layer. In many cases, zero-shot OOD generalisation using earlier-layer representations approaches the few-shot performance of retraining on penultimate layer representations. This is confirmed across multiple datasets, architectures, and types of distribution shifts. Our analysis suggests that intermediate layers are less sensitive to distribution shifts compared to the penultimate layer. These findings highlight the importance of understanding how information is distributed across network layers and its role in OOD generalisation, while also pointing to the limits of penultimate layer representation utility. Code is available at https://github.com/oshapio/intermediate-layer-generalization

Predicting player behavior in strategic games, especially complex ones like chess, presents a significant challenge. The difficulty arises from several factors. First, the sheer number of potential outcomes stemming from even a single position, starting from the initial setup, makes forecasting a player's next move incredibly complex. Second, and perhaps even more challenging, is the inherent unpredictability of human behavior. Unlike the optimized play of engines, humans introduce a layer of variability due to differing playing styles and decision-making processes. Each player approaches the game with a unique blend of strategic thinking, tactical awareness, and psychological tendencies, leading to diverse and often unexpected actions. This stylistic variation, combined with the capacity for creativity and even irrational moves, makes predicting human play difficult. Chess, a longstanding benchmark of artificial intelligence research, has seen significant advancements in tools and automation. Engines like Deep Blue, AlphaZero, and Stockfish can defeat even the most skilled human players. However, despite their exceptional ability to outplay top-level grandmasters, predicting the moves of non-grandmaster players, who comprise most of the global chess community -- remains complicated for these engines. This paper proposes a novel approach combining expert knowledge with machine learning techniques to predict human players' next moves. By applying feature engineering grounded in domain expertise, we seek to uncover the patterns in the moves of intermediate-level chess players, particularly during the opening phase of the game. Our methodology offers a promising framework for anticipating human behavior, advancing both the fields of AI and human-computer interaction.

A foundational framework within the literature on inflation dynamics is the Phillips Curve (PC) model. The Phillips Curve posits a short-term trade-off between inflation and a measure of economic slack, typically proxied by unemployment rate, such that higher inflation is associated with lower slack in the economy and vice-versa. The earliest empirical validation of this relationship, based on wage inflation and unemployment rate was provided by Phillips (1958) for the United Kingdom. Since then, the Phillips Curve framework has undergone significant theoretical advancements, culminating in the development of the micro-founded New Keynesian Phillips Curve (NKPC) (Taylor, 1980; Calvo, 1983a; Gali and Gertler, 1999) as the workhorse model for inflation analysis. Despite its theoretical appeal, the practical application of the NKPC for inflation modelling and forecasting--particularly within central banks--has been fraught with challenges. Such difficulties stem from structural breaks, state dependencies, and intrinsic nonlinearities in the relationship between inflation and its fundamental determinants, complicating its empirical validity and predictive performance (see Cristini and Ferri, 2021).