Search Results for author:
Found 16 papers, 9 papers with code
The Benefits of Balance: From Information Projections to Variance Reduction
Data balancing across multiple modalities/sources appears in various forms in several foundation models (e. g., CLIP and DINO) achieving universal representation learning.
A Primal-Dual Algorithm for Faster Distributionally Robust Optimization
We consider the penalized distributionally robust optimization (DRO) problem with a closed, convex uncertainty set, a setting that encompasses the $f$-DRO, Wasserstein-DRO, and spectral/$L$-risk formulations used in practice.
Distributionally Robust Optimization with Bias and Variance Reduction
We consider the distributionally robust optimization (DRO) problem with spectral risk-based uncertainty set and $f$-divergence penalty.
Stochastic Optimization for Spectral Risk Measures
Spectral risk objectives - also called $L$-risks - allow for learning systems to interpolate between optimizing average-case performance (as in empirical risk minimization) and worst-case performance on a task.
Deep Unlearning via Randomized Conditionally Independent Hessians
For models which require no training (k-NN), simply deleting the closest original sample can be effective.
Towards a theory of out-of-distribution learning
Establishing proper and universally agreed-upon definitions for these learning setups is essential for thoroughly exploring the evolution of ideas across different learning scenarios and deriving generalized mathematical bounds for these learners.
Scaling Recurrent Models via Orthogonal Approximations in Tensor Trains
Using insights from differential geometry, we adapt the tensor train decomposition to construct networks with significantly fewer parameters, allowing us to train powerful recurrent networks on whole brain image volume sequences.
Manifold Oblique Random Forests: Towards Closing the Gap on Convolutional Deep Networks
In particular, Forests dominate other methods in tabular data, that is, when the feature space is unstructured, so that the signal is invariant to a permutation of the feature indices.
DUAL-GLOW: Conditional Flow-Based Generative Model for Modality Transfer
Motivated by developments in modality transfer in vision, we study the generation of certain types of PET images from MRI data.
Independence Testing for Temporal Data
While many non-parametric and universally consistent dependence measures have recently been proposed, directly applying them to temporal data can inflate the p-value and result in an invalid test.
hyppo: A Multivariate Hypothesis Testing Python Package
We introduce hyppo, a unified library for performing multivariate hypothesis testing, including independence, two-sample, and k-sample testing.
Random Forests for Adaptive Nearest Neighbor Estimation of Information-Theoretic Quantities
Information-theoretic quantities, such as conditional entropy and mutual information, are critical data summaries for quantifying uncertainty.
Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
In the latter case, the optimization is often non-differentiable and also not very amenable to derivative-free optimization methods.
Sampling-free Uncertainty Estimation in Gated Recurrent Units with Exponential Families
There has recently been a concerted effort to derive mechanisms in vision and machine learning systems to offer uncertainty estimates of the predictions they make.
Robust Blind Deconvolution via Mirror Descent
We revisit the Blind Deconvolution problem with a focus on understanding its robustness and convergence properties.
Finding Differentially Covarying Needles in a Temporally Evolving Haystack: A Scan Statistics Perspective
Recent results in coupled or temporal graphical models offer schemes for estimating the relationship structure between features when the data come from related (but distinct) longitudinal sources.
