30 accepted papers
Differential privacy (DP) imposes fundamental trade-offs between privacy and statistical fidelity in synthetic data generation. While access to public data has been shown to improve these trade-offs empirically, existing approaches exploit public data only indirectly, through pre-processing (e.g., u…
We prove the conjecture stated in Appendix F.3 of Zhu et al.: among all conversion rules that map a Rényi Differential Privacy (RDP) profile $\tau \mapsto \rho(\tau)$ to a valid hypothesis-testing trade-off $f$ (or equivalently, an $(\varepsilon,\delta)$-Differential Privacy curve), the rule based o…
The standard way to evaluate language models on subjective tasks is through pairwise comparisons: an annotator chooses the "better" of two model responses for a given prompt. These comparisons are then aggregated into a single ranking via the Bradley–Terry (BT) framework, forcing heterogeneous prefe…
Translating the internal representations and computations of models into concepts that humans can understand is a key goal of interpretability. While recent dictionary learning methods such as Sparse Autoencoders (SAEs) provide a promising route to discover human-interpretable features, they often o…
Large language model (LLM) watermarks enable authentication of text provenance, curb misuse of machine-generated text, and promote trust in AI systems. Current watermarks operate by changing the next-token predictions output by an LLM. The updated (i.e., watermarked) predictions depend on random si…
A common paradigm to improve the performance of large language models is optimizing for a reward model. Reward models assign a numerical score to an LLM’s output that indicates, for example, how likely it is to align with user preferences or safety goals. However, reward models are never perfect. Th…
We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing Rényi DP, a variant of DP, under a cost constraint. Rényi DP has the advantage that by considering different values of the Rényi parameter $\alpha…
Machine learning models are routinely used to support decisions that affect individuals -- be it to screen a patient for a serious illness or to gauge their response to treatment. In these tasks, we are limited to learning models from datasets with noisy labels. In this paper, we study the instance-…
In AI research and practice, rigor remains largely understood in terms of methodological rigor---such as whether mathematical, statistical, or computational methods are correctly applied. We argue that this narrow conception of rigor has contributed to the concerns raised by the responsible AI commu…
Differentially private (DP) mechanisms are difficult to interpret and calibrate because existing methods for mapping standard privacy parameters to concrete privacy risks---re-identification, attribute inference, and data reconstruction---are both overly pessimistic and inconsistent. In this work, w…
Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to limit the risk of information leakage. The scale of the added noise is critical, as it determines the trade-off between…
The Right to be Forgotten is a core principle outlined by regulatory frameworks such as the EU’s General Data Protection Regulation (GDPR). This principle allows individuals to request that their personal data be deleted from deployed machine learning models. While "forgetting" can be naively achiev…
CLIP embeddings have demonstrated remarkable performance across a wide range of multimodal applications. However, these high-dimensional, dense vector representations are not easily interpretable, limiting our understanding of the rich structure of CLIP and its use in downstream applications that r…
Image search and retrieval tasks can perpetuate harmful stereotypes, erase cultural identities, and amplify social disparities. Current approaches to mitigate these representational harms balance the number of retrieved items across population groups defined by a small number of (often binary) attri…
Feature attribution methods explain black-box machine learning (ML) models by assigning importance scores to input features. These methods can be computationally expensive for large ML models. To address this challenge, there have been increasing efforts to develop amortized explainers, where a ML…
Missing values in real-world data pose a significant and unique challenge to algorithmic fairness. Different demographic groups may be unequally affected by missing data, and the standard procedure for handling missing values where first data is imputed, then the imputed data is used for classificat…
Machine learning (ML) models can underperform on certain population groups due to choices made during model development and bias inherent in the data. We categorize sources of discrimination in the ML pipeline into two classes: aleatoric discrimination, which is inherent in the data distribution, an…
Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples---a phenomenon known as predictive multiplicity. We demonstrate that fairness interventions in machine learning optimized solely for group fairness and a…
We characterize the differential privacy guarantees of privacy mechanisms in the large-composition regime, i.e., when a privacy mechanism is sequentially applied a large number of times to sensitive data. Via exponentially tilting the privacy loss random variable, we derive a new formula for the pri…
We consider the problem of producing fair probabilistic classifiers for multi-class classification tasks. We formulate this problem in terms of ``projecting'' a pre-trained (and potentially unfair) classifier onto the set of models that satisfy target group-fairness requirements. The new, projected…
Machine learning models are often personalized by using group attributes that encode personal characteristics (e.g., sex, age group, HIV status). In such settings, individuals expect to receive more accurate predictions in return for disclosing group attributes to the personalized model. We study wh…
Predictive multiplicity occurs when classification models with statistically indistinguishable performances assign conflicting predictions to individual samples. When used for decision-making in applications of consequence (e.g., lending, education, criminal justice), models developed without regard…
Optimization is a key component for training machine learning models and has a strong impact on their generalization. In this paper, we consider a particular optimization method---the stochastic gradient Langevin dynamics (SGLD) algorithm---and investigate the generalization of models trained by SGL…
We propose a general, yet simple patch that can be applied to existing regularization-based continual learning methods called classifier-projection regularization (CPR). Inspired by both recent results on neural networks with wide local minima and information theory, CPR adds an additional regulariz…
Identifying features that leak information about sensitive attributes is a key challenge in the design of information obfuscation mechanisms. In this paper, we propose a framework to identify information-leaking features via information density estimation. Here, features whose information densities…
This paper considers fair probabilistic classification where the outputs of primary interest are predicted probabilities, commonly referred to as scores. We formulate the problem of transforming scores to satisfy fairness constraints while minimizing the loss in utility. The formulation can be appli…
Prediction problems often admit competing models that perform almost equally well. This effect challenges key assumptions in machine learning when competing models assign conflicting predictions. In this paper, we define predictive multiplicity as the ability of a prediction problem to admit competi…
When the performance of a machine learning model varies over groups defined by sensitive attributes (e.g., gender or ethnicity), the performance disparity can be expressed in terms of the probability distributions of the input and output variables over each group. In this paper, we exploit this fact…
Non-discrimination is a recognized objective in algorithmic decision making. In this paper, we introduce a novel probabilistic formulation of data pre-processing for reducing discrimination. We propose a convex optimization for learning a data transformation with three goals: controlling discriminat…
Automatic forecasting of time series data is a challenging problem in many industries. Current forecast models adopted by businesses do not provide adequate means for including data representing external factors that may have a significant impact on the time series, such as weather, national events,…