arXiv research

Develops DP-SCD for stochastic coordinate descent, making it differentially private.

A new DP method for deep learning with faster convergence and better privacy.

Generative model disentangles dark matter halo properties.

Many powerful machine learning models are based on the composition of multiple processing layers, such as deep nets, which gives rise to nonconvex objective functions. A general, recent approach to optimise such "nested" functions is the method of auxiliary coordinates (MAC). MAC introduces an auxiliary coordinate for …

In science and engineering, intelligent processing of complex signals such as images, sound or language is often performed by a parameterized hierarchy of nonlinear processing layers, sometimes biologically inspired. Hierarchical systems (or, more generally, nested systems) offer a way to generate complex mappings usin…

New method speeds up inference for non-conjugate Gaussian processes.

In supervised binary hashing, one wants to learn a function that maps a high-dimensional feature vector to a vector of binary codes, for application to fast image retrieval. This typically results in a difficult optimization problem, nonconvex and nonsmooth, because of the discrete variables involved. Much work has sim…

New method uses correlated auxiliary feedback to reduce regret in parameterized bandits.

Aux-NAS uses auxiliary labels to improve primary task performance without extra inference cost.

Auxiliary Tuning adapts pre-trained models for novel tasks efficiently.

Learning with auxiliary tasks can improve the ability of a primary task to generalise. However, this comes at the cost of manually labelling auxiliary data. We propose a new method which automatically learns appropriate labels for an auxiliary task, such that any supervised learning task can be improved without requiri…

Method reweights auxiliary tasks to reduce data need for main task.

This paper reviews dMTL and methods for selecting auxiliary tasks.

Proposes a method to improve graph neural networks on heterogeneous graphs using meta-paths.

Pursuit-evasion is a multi-agent sequential decision problem wherein a group of agents known as pursuers coordinate their traversal of a spatial domain to locate an agent trying to evade them. Pursuit evasion problems arise in a number of import application domains including defense and route planning. Learning to opti…

AuxiLearn combines auxiliary tasks into a single loss function.

A method for constructing tight prediction intervals for multiple numerical outputs.

Researchers identify valid auxiliary functions for extreme value distributions and their max-domains of attraction.

We show that the auxiliary variable method (Møller et al., 2006; Murray et al., 2006) for inference of Markov random fields can be viewed as an approximate Bayesian computation method for likelihood estimation.

MFAI uses gradient boosted trees to leverage auxiliary info for scalable Bayesian matrix factorization.

NeurT-FDR controls FDR by incorporating auxiliary covariates in deep learning.

ScoreFusion fuses multiple diffusion models to enhance generative modeling of a target population.

An attractive approach for fast search in image databases is binary hashing, where each high-dimensional, real-valued image is mapped onto a low-dimensional, binary vector and the search is done in this binary space. Finding the optimal hash function is difficult because it involves binary constraints, and most approac…

Statistical inference is considered for variables of interest, called primary variables, when auxiliary variables are observed along with the primary variables. We consider the setting of incomplete data analysis, where some primary variables are not observed. Utilizing a parametric model of joint distribution of prima…

In intractable, undirected graphical models, an intuitive way of creating structured mean field approximations is to select an acyclic tractable subgraph. We show that the hardness of computing the objective function and gradient of the mean field objective qualitatively depends on a simple graph property. If the tract…

Enhances machine learning with background knowledge through feature generation.

Identifying coordinate transformations that make strongly nonlinear dynamics approximately linear is a central challenge in modern dynamical systems. These transformations have the potential to enable prediction, estimation, and control of nonlinear systems using standard linear theory. The Koopman operator has emerged…

Proposes a Thompson sampling algorithm for multi-objective contextual bandit problems with auxiliary constraints.

Perry uses auxiliary data to estimate RL policy values with confidence intervals.

Improves deep learning models by blending gradients from training loss and auxiliary objective.

Dimensionality reduction (DR) is often used as a preprocessing step in classification, but usually one first fixes the DR mapping, possibly using label information, and then learns a classifier (a filter approach). Best performance would be obtained by optimizing the classification error jointly over DR mapping and cla…

We propose a probabilistic model for refining coarse-grained spatial data by utilizing auxiliary spatial data sets. Existing methods require that the spatial granularities of the auxiliary data sets are the same as the desired granularity of target data. The proposed model can effectively make use of auxiliary data set…

Constructs metrics with Q-curvature on manifolds with singularities.

Extends Wigner's representation to study super hyperbolic geometry.

A new method solves complex control problems with random coefficients.

Auxiliary equations improve bounds in symplectic geometry.

New algorithm reduces learning regret in multi-agent systems with unknown dynamics.

Deep learning method solves American options with free boundary using Landau transformation.

We propose a new optimization method for training feed-forward neural networks. By rewriting the activation function as an equivalent proximal operator, we approximate a feed-forward neural network by adding the proximal operators to the objective function as penalties, hence we call the lifted proximal operator machin…

A method corrects bias in estimating a high-dimensional classification rule using auxiliary outcomes.

LRSAO uses RL to dynamically select and unlearn auxiliary objectives for EA optimization.

We introduce a generic scheme for accelerating gradient-based optimization methods in the sense of Nesterov. The approach, called Catalyst, builds upon the inexact accelerated proximal point algorithm for minimizing a convex objective function, and consists of approximately solving a sequence of well-chosen auxiliary p…

Unified framework for lifted training and inversion of neural networks.

This note compares two recently published machine learning methods for constructing flexible, but tractable families of variational hidden-variable posteriors. The first method, called "hierarchical variational models" enriches the inference model with an extra variable, while the other, called "auxiliary deep generati…

In this paper we study the Weil-Petersson geometry of $\overline{\mathcal{M}_{g,n}}$, the compactified moduli space of Riemann surfaces with genus g and n marked points. The main goal of this paper is to understand the growth of the diameter of $\overline{\mathcal{M}_{g,n}}$ as a function of $g$ and $n$. We show that t…

A method for camera calibration using heatmap regression for fisheye images.

FedAUX improves Federated Learning by better using unlabeled data.

In-N-Out improves model robustness to out-of-distribution data.