Related papers: NOMAD version 4: Nonlinear optimization with the M…
This paper develops a scalable new algorithm, called NysADMM, to minimize a smooth convex loss function with a convex regularizer. NysADMM accelerates the inexact Alternating Direction Method of Multipliers (ADMM) by constructing a…
Automated algorithm selection for continuous black-box optimization depends on representing problem information under limited probing and selecting solvers under heavy-tailed performance distributions. This paper proposes a geometric…
Automata learning has been successfully applied in the verification of hardware and software. The size of the automaton model learned is a bottleneck for scalability, and hence optimizations that enable learning of compact representations…
A novel algorithm for wide-baseline matching called MODS - Matching On Demand with view Synthesis - is presented. The MODS algorithm is experimentally shown to solve a broader range of wide-baseline problems than the state of the art while…
We study the Regularized A-optimal Design (RAOD) problem, which selects a subset of $k$ experiments to minimize the inverse of the Fisher information matrix, regularized with a scaled identity matrix. RAOD has broad applications in Bayesian…
Recently, the expert-crafted neural architectures is increasing overtaken by the utilization of neural architecture search (NAS) and automatic generation (and tuning) of network structures which has a close relation to the Hyperparameter…
We introduce Robust Multi-Objective Decoding (RMOD), a novel inference-time algorithm that robustly aligns Large Language Models (LLMs) to multiple human objectives (e.g., instruction-following, helpfulness, safety) by maximizing the…
Out of distribution (OOD) detection remains a critical challenge in malware classification due to the substantial intra family variability introduced by polymorphic and metamorphic malware variants. Most existing deep learning based malware…
Contemporary text-to-image models exhibit a surprising degree of mode collapse, as can be seen when sampling several images given the same text prompt. Previous work has attempted to address this issue by steering the model using guidance…
In this paper we introduce a new classification algorithm called Optimization of Distributions Differences (ODD). The algorithm aims to find a transformation from the feature space to a new space where the instances in the same class are as…
NOMAD CAMELS (short: CAMELS) is a configurable, open-source measurement software that records fully self-describing experimental data. It has its origins in the field of experimental physics where a wide variety of measurement instruments…
Aircraft industry is constantly striving for more efficient design optimization methods in terms of human efforts, computation time, and resource consumption. Hybrid surrogate optimization maintains high results quality while providing…
Recent advances on Out-of-Distribution (OoD) generalization reveal the robustness of deep learning models against distribution shifts. However, existing works focus on OoD algorithms, such as invariant risk minimization, domain…
System design tools are often only available as input-output blackboxes: for a given design as input they compute an output representing system behavior. Blackboxes are intended to be run in the forward direction. This paper presents a new…
Graph Out-of-Distribution (OOD) classification often suffers from sharp performance drops, particularly under category imbalance and structural noise. This work tackles two pressing challenges in this context: (1) the underperformance of…
Graduated optimization is a global optimization technique that is used to minimize a multimodal nonconvex function by smoothing the objective function with noise and gradually refining the solution. This paper experimentally evaluates the…
We propose Network Automatic Relevance Determination (NARD), an extension of ARD for linearly probabilistic models, to simultaneously model sparse relationships between inputs $X \in \mathbb R^{d \times N}$ and outputs $Y \in \mathbb R^{m…
Learned optimizers -- neural networks that are trained to act as optimizers -- have the potential to dramatically accelerate training of machine learning models. However, even when meta-trained across thousands of tasks at huge…
Deep neural networks are getting larger. Their implementation on edge and IoT devices becomes more challenging and moved the community to design lighter versions with similar performance. Standard automatic design tools such as…
We introduce a new adaptive decomposition tool, which we refer to as Nonlinear Mode Decomposition (NMD). It decomposes a given signal into a set of physically meaningful oscillations for any waveform, simultaneously removing the noise. NMD…