arXiv research

Proposes ConstraintMatch for semi-supervised clustering with unconstrained data.

Unconstrained models learn physical symmetries effectively with simple data augmentation.

VoxCeleb 2019 challenge assesses speaker recognition in uncontrolled settings.

Unconstrained MLIPs outperform constrained ones in accuracy and speed.

Our paper explains deep neural collapse in multiple layers.

New approach reduces unconstrained linear bandits to simpler optimization problems.

We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is conditionally independent of group membership given the score. We show that under r…

This paper extends neural collapse to imbalanced data under cross-entropy loss.

Develops parameter-free online mirror descent for optimal dynamic regret.

We study optimization methods for solving the maximum likelihood formulation of independent component analysis (ICA). We consider both the the problem constrained to white signals and the unconstrained problem. The Hessian of the objective function is costly to compute, which renders Newton's method impractical for lar…

A new optimization algorithm improves convergence in unconstrained problems.

New sparse Gaussian process method tackles unconstrained regression problems.

The paper explores solving inverse problems for ODEs with and without constraints.

DP-GD achieves dimension-independent convergence for unconstrained private GLMs.

Quantum computing improves feature selection in machine learning.

Develops methods for estimating constrained function-valued parameters in infinite-dimensional models.

This paper extends neural collapse to class-imbalanced datasets using an unconstrained ReLU feature model.

New algorithms reduce online learning regret by tracking gradient variation.

A new L-BFGS method tackles large-scale optimization with fewer evaluations.

New algorithm minimizes cumulative loss in dynamic linear bandits without prior knowledge of comparator switches.

This paper evaluates conformal prediction for aerial image classification in challenging environments.

We propose an online convex optimization algorithm (RescaledExp) that achieves optimal regret in the unconstrained setting without prior knowledge of any bounds on the loss functions. We prove a lower bound showing an exponential separation between the regret of existing algorithms that require a known bound on the los…

The paper analyzes reflected diffusion models on hypercube data.

VAV method optimizes learning rate for faster, stable SGD convergence.

We consider a variant of online convex optimization in which both the instances (input vectors) and the comparator (weight vector) are unconstrained. We exploit a natural scale invariance symmetry in our unconstrained setting: the predictions of the optimal comparator are invariant under any linear transformation of th…

A new algorithm solves nonnegative least squares faster with nonnegative data.

Solves VaR-constrained portfolio optimization in markets with stochastic volatility.

Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem. This paper proposes an approach that couples a deep CNN-based approach with a low-dimensional discriminative embedding learned using triplet probability constraints to solve the unconstraine…

Cookbook transforms constrained statistical inference into unconstrained problems.

For technology (like serious games) that aims to deliver interactive learning, it is important to address relevant mental experiences such as reflective thinking during problem solving. To facilitate research in this direction, we present the weDraw-1 Movement Dataset of body movement sensor data and reflective thinkin…

Yau's Affine Normal Descent optimizes smooth unconstrained problems with geometrically adapted directions.

Study optimal portfolio management with periodic evaluations in stochastic models, considering convex constraints.

This paper analyzes the landscape of supervised contrastive loss in over-parameterized networks.

Adam converges with high probability under unconstrained non-convex smooth stochastic optimizations.

New method parameterizes solutions to linearized vacuum constraints on Einstein manifolds.

Paper analyzes regret bounds for unconstrained online optimization.

A drawdown constraint forces the current wealth to remain above a given function of its maximum to date. We consider the portfolio optimisation problem of maximising the long-term growth rate of the expected utility of wealth subject to a drawdown constraint, as in the original setup of Grossman and Zhou (1993). We wor…

New methods solve complex optimization problems in machine learning.

CMPE improves SBI efficiency and accuracy.

This article presents a new methodology called deep Theory of Functional Connections (TFC) that estimates the solutions of partial differential equations (PDEs) by combining neural networks with TFC. TFC is used to transform PDEs with boundary conditions into unconstrained optimization problems by embedding the boundar…

The paper studies knot densities under various constraints and degenerations.

Paper adapts diffusion sampler training for faster convergence and better sampling.

Training shapes the geometry of neural network feature maps, revealing local area magnification.

In this paper, we introduce a novel and robust approach to Quantized Matrix Completion (QMC). First, we propose a rank minimization problem with constraints induced by quantization bounds. Next, we form an unconstrained optimization problem by regularizing the rank function with Huber loss. Huber loss is leveraged to c…

We consider minimizing a nonconvex, smooth function $f$ on a Riemannian manifold $\mathcal{M}$. We show that a perturbed version of Riemannian gradient descent algorithm converges to a second-order stationary point (and hence is able to escape saddle points on the manifold). The rate of convergence depends as $1/ε^2$ o…

Proposes an evolutionary approach to fitting acyclic VAR models.

Paper proves fair classification can be done via simple thresholding.

Unified CCA methods for large-scale data with fast SGD algorithms.