MLINFO COLLECTION
We study Gaussian kernel approximation and regularized logistic classification on a connected compact smooth embedded manifold $X\subset\mathbb R^d$ without boundary and of intrinsic dimension…
Neural Posterior Estimation (NPE) fits an amortized conditional density estimator to a simulated training set of complete-data realizations. NPE's training objective, log-likelihood, favors posterior…
Bayesian Causal Forests (BCF) estimate heterogeneous treatment effects with a separate ensemble of treatment trees. The prior on the leaf values of the treatment trees determines whether sampling…
Facing imbalanced binary classification, we aim at maximizing the recall while limiting the proportion of false detections in the minority class. For doing that, the present work studies the effect…
This paper considers the Bayesian top-$k$ identification problem, wherein a decision maker is tasked with selecting $k$ items from a pool of items of unknown quality. To assess the items, the…
Architectural and structural design optimization in parametric software affords about a thousand evaluations of an expensive model for problems with tens of variables, a regime for which most…
In multi-group learning, a single predictor must control its excess risk simultaneously over overlapping groups. Tosh and Hsu (2022) obtained $1/\sqrt{n}$ slow rates via a reduction to online…
We study federated spectral estimation when a large matrix is horizontally partitioned across servers that cannot share raw data. We propose FLICKER, a target-specific gradient-based power iteration…
Direct Preference Optimization (DPO) learns from pairwise preferences through a logistic objective whose score-difference parameterization follows the Bradley--Terry model. We study how failure of…
Exact demographic parity requires the same prediction distribution across sensitive groups. In regression, this can be too restrictive and reduce predictive accuracy.
Digital art generation has undergone a massive paradigm shift, moving from static image synthesis to dynamic video generation that can mimic the human painting process. While existing models can…
Synthesizing a monocular video from a new camera trajectory requires preserving the observed scene geometry and motion while completing regions that become newly visible. Feed-forward 4D…
A guardrail classifier is reported as if unsafe were a property of text. It is not: it is a property of a policy, and the policy enters the model through its labels.
Under the quantifier $\exists A\,\forall D$, where the realizable distribution and its marginal are unknown, we determine the finite-class sample-complexity exponent for strict replicability: two…
Web platforms organize collective work, including content review and community maintenance, that imposes heterogeneous effort costs on participants. Fairly distributing these burdens while leaving as…
Networks of repeated neural modules with delayed neighbour coupling need stability guarantees for every number of modules, but delay-dependent criteria certify one network at a time and grow with its…
Distribution regression seeks to learn mappings from probability distributions to response variables and has emerged as a unifying framework for kernel methods, multi-instance learning, and…
Cox processes provide a principled Bayesian nonparametric framework for modeling event-based data through an underlying intensity function. However, existing inference methods for estimating the…
We study nonconvex--strongly-convex bilevel optimization with finite-sum objectives and fully first-order oracles. We propose Sampled Implicit Corrections for Bilevel Optimization (SICBO), which…
Recursive self-improvement (RSI) relies on evaluation feedback to assess progress and guide further research, yet repeatedly running complex benchmarks is costly and slows iteration. Human experts…
A universal forecaster is trained once and applied everywhere, so it must serve tasks whose schemas, forecast horizons, and temporal resolutions all differ. The number of targets and covariates…
Generating time-to-event data is increasingly important in survival analysis, but it remains statistically challenging because event times are often censored and thus prevent flexible generative…
Understanding how stochastic gradient descent learns internal representations in wide neural networks trained on rich target functions is a central problem in machine learning. We study this question…
Learning causal structure from data requires assumptions about mechanisms, noises, observation schemes, and interventions. Historically, causal discovery has relied primarily on conditional…