arXiv research

Heuristic algorithm for portfolio optimization reduces solve times to milliseconds.

The paper solves optimal bounds for separating data points in high dimensions.

The paper extends optimal transport for linear separability of sheared distributions in supervised learning.

New algorithm AG-OG optimizes separable convex-concave problems efficiently.

Adaptive algorithm reduces regret in causal bandits.

Study optimizes fairness in predictive models by balancing utility and separation.

Mixup reduces the sample complexity of finding optimal decision boundaries for more separable data.

Paper optimizes hyperspherical prototypes for better class separation.

EM algorithm achieves optimal sample complexity for well-separated Gaussian mixtures.

Adam optimizes linear classifiers with separable data.

AutoClip automatically adjusts gradient clipping for better audio separation.

We present an alternating augmented Lagrangian method for convex optimization problems where the cost function is the sum of two terms, one that is separable in the variable blocks, and a second that is separable in the difference between consecutive variable blocks. Examples of such problems include Fused Lasso estima…

This work investigates implicit bias in multiclass separable data using a novel geometry-aware optimizer.

Stochastic Neighbor Embedding and its variants are widely used dimensionality reduction techniques -- despite their popularity, no theoretical results are known. We prove that the optimal SNE embedding of well-separated clusters from high dimensions to any Euclidean space R^d manages to successfully separate the cluste…

New deep-unfolded network improves video background separation.

The paper establishes a nearly-sharp statistical threshold for efficient learning in Latent MDPs with separated components.

Proposes a two-step method for sound source separation.

Paper proposes CNN-LSTM model for multi-speaker speech separation.

New findings show sampling vs optimization are incomparable in non-convex cases.

Reservoir computing's success depends on mapping different input time series to separable states.

In this paper we show that two seemingly unrelated problems in economics, the hypothesis of integrability and the hypothesis of additive separability are linked by the absence of curvature of connections on webs naturally associated with each problem.

Singing voice separation attempts to separate the vocal and instrumental parts of a music recording, which is a fundamental problem in music information retrieval. Recent work on singing voice separation has shown that the low-rank representation and informed separation approaches are both able to improve separation qu…

This paper proposes an alternative algorithm for multichannel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable in its impressive source separation performance, the convergence-guaranteed optimization algorithm and that it allows us to estimate source-cla…

To overcome the oscillation problem in the classical momentum-based optimizer, recent work associates it with the proportional-integral (PI) controller, and artificially adds D term producing a PID controller. It suppresses oscillation with the sacrifice of introducing extra hyper-parameter. In this paper, we start by …

Logistic regression is one of the most popular methods in binary classification, wherein estimation of model parameters is carried out by solving the maximum likelihood (ML) optimization problem, and the ML estimator is defined to be the optimal solution of this problem. It is well known that the ML estimator exists wh…

PPG separates policy and value function training phases for better reinforcement learning efficiency.

A new algorithm finds a separating hyperplane with fewer updates.

New algorithms reduce slate bandit regret for large slates, outperforming existing methods.

Separates estimation and control in risk-sensitive investment problems with partial observation.

Optimal ReLU networks can memorize any separable set of points with a small number of parameters.

TiAda adapts adaptive gradient methods for nonconvex minimax optimization.

A new method separates data points using entropy minimization over a hypercube.

Optimal transport as a loss for machine learning optimization problems has recently gained a lot of attention. Building upon recent advances in computational optimal transport, we develop an optimal transport non-negative matrix factorization (NMF) algorithm for supervised speech blind source separation (BSS). Optimal …

Inverse Drum Machine separates drum mixes using transcription and synthesis.

Gradient methods avoid overfitting on separable data.

The paper improves RPCA for separating sparse and manifold components on noisy data.

slimTrain simplifies DNN training by separating features and adapting hyperparameters.

Mirror flow optimizes separable data problems, converging to a maximum margin classifier.

PeL separates sensory interface optimization from decision learning.

Study timelike Ricci curvature bounds via optimal transport with Orlicz-type costs.

We study exact recovery conditions for convex relaxations of point cloud clustering problems, focusing on two of the most common optimization problems for unsupervised clustering: $k$-means and $k$-median clustering. Motivations for focusing on convex relaxations are: (a) they come with a certificate of optimality, and…

We study the Merton problem of optimal consumption-investment for the case of two investors sharing a final wealth. The typical example would be a husband and wife sharing a portfolio looking to optimize the expected utility of consumption and final wealth. Each agent has different utility function and discount factor.…

We consider Aubry-Mather theory for a subclass of class A spacetimes, i.e. compact vicious spacetimes with globally hyperbolic Abelian cover. In this subclass, called class A_1, we obtain improved results on timelike maximizers and Lipschitz continuity of the time separation of the Abelian cover on the i.g. optimal sub…

This paper investigates how data augmentation improves linear separation of manifold data.

Sparse Blind Source Separation (sparse BSS) is a key method to analyze multichannel data in fields ranging from medical imaging to astrophysics. However, since it relies on seeking the solution of a non-convex penalized matrix factorization problem, its performances largely depend on the optimization strategy. In this …

Paper proposes graph-based separable transforms for video coding.

A new framework uses deep reinforcement learning to improve aircraft separation in busy airspace.

We develop randomized (block) coordinate descent (CD) methods for linearly constrained convex optimization. Unlike most CD methods, we do not assume the constraints to be separable, but let them be coupled linearly. To our knowledge, ours is the first CD method that allows linear coupling constraints, without making th…