Search Results

In this paper, we propose the Whiplash inertial gradient dynamics, a closed‐loop optimization method that utilizes gradient information. We introduce the symplectic asymptotic convergence analysis for the Whiplash system for convex functions. We ...

Can we accelerate the convergence of gradient descent without changing the algorithm—just by judiciously choosing stepsizes? Surprisingly, we show that the answer is yes. Our proposed Silver Stepsize Schedule optimizes strongly convex functions in \(\(\...\)

Compressed sensing has been a very successful high-dimensional signal acquisition and recovery technique that relies on linear operations. However, the actual measurements of signals have to be quantized before storing or processing them. One-bit ...

Gradient-based optimization is now ubiquitous across graphics, but unfortunately can not be applied to problems with undefined or zero gradients. To circumvent this issue, the loss function can be manually replaced by a "surrogate" that has similar ...

Learning to bid in repeated first-price auctions is a fundamental problem at the interface of game theory and machine learning, which has seen a recent surge in interest due to the transition of display advertising to first-price auctions. In this work, ...

Recently proposed gradient estimators enable gradient descent over stochastic programs with discrete jumps in the response surface, which are not covered by automatic differentiation (AD) alone. Although these estimators’ capability to guide a ...

Increasing effort is put into the development of methods for learning mechanistic models from data. This task entails not only the accurate estimation of parameters but also a suitable model structure. Recent work on the discovery of dynamical systems ...

This paper is dedicated to an optimization problem. Let A, B ⊂ be compact convex sets. Consider the minimal number t⁰ > 0 such that t⁰B covers A after a shift to a vector x⁰ ∈ . The goal is to find t⁰ and x⁰. In the special case of B being a unit ...

Fizzer is a new gray-box fuzzer. In contrast to common gray-box fuzzers that aim to cover both true and false branches of branching instructions, Fizzer primarily aims to cover both possible values true and false of Boolean expressions in the ...

State-of-the-art hypergraph partitioners, such as hMETIS, usually adopt a multi-level paradigm for efficiency and scalability. However, they are prone to getting trapped in local minima due to their reliance on refinement heuristics and overlooking ...

We produce thickness and bone to soft tissue ratio estimations from a single, 2D medical X-ray image. For this, we simulate the scattering of the rays through a model of the object and embed this simulation into an optimiser which iteratively adjusts ...

As musculoskeletal illnesses continue to increase, practical computerised muscle modelling is crucial. This paper addresses this concern by proposing a mathematical model for a dynamic 3D geometrical surface representation of muscles using a Radial Basis ...

When dealing with difficult inverse problems such as inverse rendering, using Monte Carlo estimated gradients to optimise parameters can slow down convergence due to variance. Averaging many gradient samples in each iteration reduces this variance ...

Social media have great potential for enabling public discourse on important societal issues. However, adverse effects, such as polarization and echo chambers, greatly impact the benefits of social media and call for algorithms that mitigate these ...

Symbolic regression is a common problem in genetic programming (GP), but the syntactic search carried out by the standard GP algorithm often struggles to tune the learned expressions. On the other hand, gradient-based optimizers can efficiently tune ...

The aim of Symbolic Regression (SR) is to discover interpretable expressions that accurately describe data. The accuracy of an expression depends on both its structure and coefficients. To keep the structure simple enough to be interpretable, ...

Accelerated Algorithms for Ranking

Assigning ranking scores to items based on observed comparison data (e.g., paired comparisons, choice, and full ranking outcomes) has been of continued interest in a wide range of applications, including information ...

The problem of assigning ranking scores to items based on observed comparison data (e.g., paired comparisons, choice, and full ranking outcomes) has been of continued interest in a wide range of applications, including information search, aggregation of ...

Inspired by the remarkable success of large neural networks, there has been significant interest in understanding the generalization performance of over-parameterized models. Substantial efforts have been invested in characterizing how optimization ...

Recent works have studied implicit biases in deep learning, especially the behavior of last-layer features and classifier weights. However, they usually need to simplify the intermediate dynamics under gradient ow or gradient descent due to the ...

We introduce two block coordinate descent algorithms for solving optimization problems with ordinary differential equations (ODEs) as dynamical constraints. In contrast to prior algorithms, ours do not need to implement sensitivity analysis methods to ...