Category
2,617 papers
We study whether benchmarks reliably guide model selection as developers adapt to evaluation feedback across multiple criteria. We find that the worst-case test-set size needed to estimate the best score among $k$ adaptively chosen models, under any convex combination of the criteria, grows exponentially with the numbe...
Multi-objective Bayesian optimization (MOBO) is commonly approached through specialized acquisition functions or scalarization schemes designed to explicitly account for trade-offs among non-preferential objectives. In this work, we show that such complexity might be unnecessary. We propose a framework that extends sta...
This paper develops a theorem-level pipeline in symmetry-quotient settings: quotient linear stability implies quotient flatness, quotient flatness implies input smoothness, and input smoothness yields generalization under local covering assumptions. Flatness is often associated with generalization, and Stochastic Gradi...
Motivated by local sleep, the use-dependent off periods of individual cortical circuits in awake animals, it is shown that replay can instead be written into the degrees of freedom the current input leaves unused.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This paper revisit the nuances of long-term fairness achievable by an ADM-- specifically, through the lens of a loan approver inducing a population-level wealth dynamics, by developing Eutopia: a lending-process simulator enabled with a novel performative data generator to learn long-term fair strategies.
SF-NorMuon, a schedule-free spectral optimizer that closes the performance gap with tuned AdamW baselines, makes horizon-free optimization more practical, taking a step towards truly open-ended, continual learning.
Instrumental-variable (IV) regression enables causal estimation under endogeneity, but modern IV problems often involve nonlinear structural effects and high-dimensional covariates. Existing methods typically operate in observed or generic learned feature spaces, and they often yield point estimates without uncertainty...
Aligning language models with human preferences is essential for ensuring their safety and reliability. Although most existing approaches assume specific human preference models such as the Bradley-Terry model, this assumption may fail to accurately capture true human preferences, and consequently, these methods lack s...
A soft regression forest decision rule is proposed that preserves the interpretability of classical decision trees while being fully parametric, differentiable, and Lipschitz-smooth, enabling intrinsic interpretation from both global and local perspectives.
Compared to both unstructured baselines and strictly equivariant models, the soft Clifford transformer achieves better long-horizon fidelity, particularly in regimes with broken symmetries, suggesting that geometric algebra offers an effective middle ground.
As demands for resource efficiency and safety in modern neural networks intensify, substantial research effort has gone into model compression and adversarial robustness. Yet despite progress on each in isolation, a systematic understanding of how compressibility shapes robustness remains elusive. In this paper, we dev...
This work identifies and characterize an interesting dichotomy in the rates achievable in the supervised setting: there is a weak transfer regime where optimal rates are determined by information in either the source or target dataset but not both, and a strong transfer regime where much faster target rates are achieva...
MIT Statistics and Data Science Center Director Alexander (Sasha) Rakhlin shares important considerations for departments and institutions.
By rethinking how large cloud computing systems operate, Associate Professor Christina Delimitrou seeks to make data centers more energy efficient.
As director, Bourg has focused on digital access, open and equitable scholarly publishing, and expanded support for data-intensive research.
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures” making it hard for AI to handle complexity. The post What AI gets wrong and what failure teaches us appeared first on Microsoft Research.
Mobile Systems
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
