Insert related papers here

Insert related papers here

Insert related papers here

Insert related papers here

Insert related papers here

Insert related papers here

Welcome to Byte Size Arxiv

Papers made digestable

2023-02-02

STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation

  • Detailed ablations also reveal the mechanism of our proposal
  • It brings meaningful new challenges to the community
  • Codes, data, and models are available at https://github.com/ucaszyp/STEPS.
Self-supervised depth estimation draws a lot of attention recently as it can promote the 3D sensing capabilities of self-driving vehicles. However, it intrinsically relies upon the photometric consistency assumption, which hardly holds during nighttime. Although various supervised nighttime image enhancement methods have been proposed, their generalization performance in challenging driving scenarios is not satisfactory. To this end, we propose the first method that jointly learns a nighttime image enhancer and a depth estimator, without using ground truth for either task. Our method tightly entangles two self-supervised tasks using a newly proposed uncertain pixel masking strategy. This strategy originates from the observation that nighttime images not only suffer from underexposed regions but also from overexposed regions. By fitting a bridge-shaped curve to the illumination map distribution, both regions are suppressed and two tasks are bridged naturally. We benchmark the method on two established datasets: nuScenes and RobotCar and demonstrate state-of-the-art performance on both of them. Detailed ablations also reveal the mechanism of our proposal. Last but not least, to mitigate the problem of sparse ground truth of existing datasets, we provide a new photo-realistically enhanced nighttime dataset based upon CARLA. It brings meaningful new challenges to the community. Codes, data, and models are available at https://github.com/ucaszyp/STEPS.

Authors: Yupeng Zheng, Chengliang Zhong, Pengfei Li, Huan-ang Gao, Yuhang Zheng, Bu Jin, Ling Wang, Hao Zhao, Guyue Zhou, Qichao Zhang, Dongbin Zhao.

2023-02-02

Lower Bounds for Learning in Revealing POMDPs

  • We establish strong PAC and regret lower bounds for learning in revealing POMDPs
  • Technically, our hard instance construction adapts techniques in \emph{distribution testing}, which is new to the RL literature and may be of independent interest.
This paper studies the fundamental limits of reinforcement learning (RL) in the challenging \emph{partially observable} setting. While it is well-established that learning in Partially Observable Markov Decision Processes (POMDPs) requires exponentially many samples in the worst case, a surge of recent work shows that polynomial sample complexities are achievable under the \emph{revealing condition} -- A natural condition that requires the observables to reveal some information about the unobserved latent states. However, the fundamental limits for learning in revealing POMDPs are much less understood, with existing lower bounds being rather preliminary and having substantial gaps from the current best upper bounds. We establish strong PAC and regret lower bounds for learning in revealing POMDPs. Our lower bounds scale polynomially in all relevant problem parameters in a multiplicative fashion, and achieve significantly smaller gaps against the current best upper bounds, providing a solid starting point for future studies. In particular, for \emph{multi-step} revealing POMDPs, we show that (1) the latent state-space dependence is at least $\Omega(S^{1.5})$ in the PAC sample complexity, which is notably harder than the $\widetilde{\Theta}(S)$ scaling for fully-observable MDPs; (2) Any polynomial sublinear regret is at least $\Omega(T^{2/3})$, suggesting its fundamental difference from the \emph{single-step} case where $\widetilde{O}(\sqrt{T})$ regret is achievable. Technically, our hard instance construction adapts techniques in \emph{distribution testing}, which is new to the RL literature and may be of independent interest.

Authors: Fan Chen, Huan Wang, Caiming Xiong, Song Mei, Yu Bai.

2023-02-02

Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval

  • We propose the first Bayesian encoder for metric learning
  • We actualize this by first proving that the contrastive loss is a valid log-posterior
  • We then propose three methods that ensure a positive definite Hessian
  • Lastly, we present a novel decomposition of the Generalized Gauss-Newton approximation.
We propose the first Bayesian encoder for metric learning. Rather than relying on neural amortization as done in prior works, we learn a distribution over the network weights with the Laplace Approximation. We actualize this by first proving that the contrastive loss is a valid log-posterior. We then propose three methods that ensure a positive definite Hessian. Lastly, we present a novel decomposition of the Generalized Gauss-Newton approximation. Empirically, we show that our Laplacian Metric Learner (LAM) estimates well-calibrated uncertainties, reliably detects out-of-distribution examples, and yields state-of-the-art predictive performance.

Authors: Frederik Warburg, Marco Miani, Silas Brack, Soren Hauberg.

2023-02-02

Evidence for suppression of structure growth in the concordance cosmological model

  • We present evidence for a suppressed growth rate of large-scale structure during the dark-energy dominated era
  • When combined, they yield $\gamma=0.633^{+0.025}_{-0.024}$, excluding $\gamma=0.55$ at a statistical significance of 3.7$\sigma$.
We present evidence for a suppressed growth rate of large-scale structure during the dark-energy dominated era. Modeling the growth rate of perturbations with the ``growth index'' $\gamma$, we find that current cosmological data strongly prefer a higher growth index than the value $\gamma=0.55$ predicted by general relativity in a flat $\Lambda$CDM cosmology. Both the cosmic microwave background data from Planck and the large-scale structure data from weak lensing, galaxy clustering, and cosmic velocities separately favor growth suppression. When combined, they yield $\gamma=0.633^{+0.025}_{-0.024}$, excluding $\gamma=0.55$ at a statistical significance of 3.7$\sigma$. The combination of $f\sigma_8$ and Planck measurements prefers an even higher growth index of $\gamma=0.639^{+0.024}_{-0.025}$, corresponding to a 4.2$\sigma$-tension with the concordance model. In Planck data, the suppressed growth rate offsets the preference for nonzero curvature and fits the data equally well as the latter model. A higher $\gamma$ leads to a higher matter fluctuation amplitude $S_8$ inferred from galaxy clustering and weak lensing measurements, and a lower $S_8$ from Planck data, effectively resolving the $S_8$ tension.

Authors: Nhat-Minh Nguyen, Dragan Huterer, Yuewei Wen.

2023-02-02

SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections

  • Our framework is learned from in-the-wild 2D image collections only, without any 3D annotations
  • The height field represents the surface elevation of 3D scenes, while the semantic field provides detailed scene semantics
  • Lastly, a neural volumetric renderer, learned from 2D image collections through adversarial training, is employed to produce photorealistic images
  • Extensive experiments demonstrate the effectiveness of SceneDreamer and superiority over state-of-the-art methods in generating vivid yet diverse unbounded 3D worlds.
In this work, we present SceneDreamer, an unconditional generative model for unbounded 3D scenes, which synthesizes large-scale 3D landscapes from random noises. Our framework is learned from in-the-wild 2D image collections only, without any 3D annotations. At the core of SceneDreamer is a principled learning paradigm comprising 1) an efficient yet expressive 3D scene representation, 2) a generative scene parameterization, and 3) an effective renderer that can leverage the knowledge from 2D images. Our framework starts from an efficient bird's-eye-view (BEV) representation generated from simplex noise, which consists of a height field and a semantic field. The height field represents the surface elevation of 3D scenes, while the semantic field provides detailed scene semantics. This BEV scene representation enables 1) representing a 3D scene with quadratic complexity, 2) disentangled geometry and semantics, and 3) efficient training. Furthermore, we propose a novel generative neural hash grid to parameterize the latent space given 3D positions and the scene semantics, which aims to encode generalizable features across scenes. Lastly, a neural volumetric renderer, learned from 2D image collections through adversarial training, is employed to produce photorealistic images. Extensive experiments demonstrate the effectiveness of SceneDreamer and superiority over state-of-the-art methods in generating vivid yet diverse unbounded 3D worlds.

Authors: Zhaoxi Chen, Guangcong Wang, Ziwei Liu.

2023-02-02

Super-frustration in a dipolar Bose-Einstein condensate introduced by an optical lattice

  • Here we consider the application of a square optical lattice to such a system
  • The 4-fold symmetry of the lattice, and the spacing set by it, competes with the intrinsic 6-fold symmetry and spacing of the dipolar droplets in the unperturbed ground state.
Dipolar Bose-Einstein condensates can form arrays of spatially distinct droplets with hexagonal symmetry on top of a small background density in what's known as the supersolid phase. Here we consider the application of a square optical lattice to such a system. The 4-fold symmetry of the lattice, and the spacing set by it, competes with the intrinsic 6-fold symmetry and spacing of the dipolar droplets in the unperturbed ground state. By developing a graphics processing unit enhanced solver to the extended Gross-Pitaevskii equation, we find that the application of the lattice can lead to frustration for certain lattice parameters while maintaining phase coherence between droplets, and thus we consider such states super-frustrated. We additionally see second-order phase transitions as a function of lattice depth and glassiness characterized by a deeply degenerate ground state manifold.

Authors: Eli J. Halperin, Shai Ronen, J. L. Bohn.

2023-02-02

Universal Secure Source Encryption under Side-Channel Attacks

  • We study the universal coding under side-channel attacks posed and investigated by Santoso and Oohama (2021).

We study the universal coding under side-channel attacks posed and investigated by Santoso and Oohama (2021). They proposed a theoretical security model for Shannon cipher system under side-channel attacks, where the adversary is not only allowed to collect ciphertexts by eavesdropping the public communication channel, but is also allowed to collect the physical information leaked by the devices where the cipher system is implemented on such as running time, power consumption, electromagnetic radiation, etc. For any distributions of the plain text, any noisy channels through which the adversary observe the corrupted version of the key, and any measurement device used for collecting the physical information, we can derive an achievable rate region for reliability and security such that if we compress the ciphertext using an affine encoder with rate within the achievable rate region, then: (1) anyone with secret key will be able to decrypt and decode the ciphertext correctly, but (2) any adversary who obtains the ciphertext and also the side physical information will not be able to obtain any information about the hidden source as long as the leaked physical information is encoded with a rate within the rate region.

Authors: Yasutada Oohama, Bagus Santoso.

2023-02-02

Double Permutation Equivariance for Knowledge Graph Completion

  • This work provides a formalization of Knowledge Graphs (KGs) as a new class of graphs that we denote doubly exchangeable attributed graphs, where node and pairwise (joint 2-node) representations must be equivariant to permutations of both node ids and edge (& node) attributes (relations & node features)
  • Double-permutation equivariant KG representations open a new research direction in KGs.
This work provides a formalization of Knowledge Graphs (KGs) as a new class of graphs that we denote doubly exchangeable attributed graphs, where node and pairwise (joint 2-node) representations must be equivariant to permutations of both node ids and edge (& node) attributes (relations & node features). Double-permutation equivariant KG representations open a new research direction in KGs. We show that this equivariance imposes a structural representation of relations that allows neural networks to perform complex logical reasoning tasks in KGs. Finally, we introduce a general blueprint for such equivariant representations and test a simple GNN-based double-permutation equivariant neural architecture that achieve 100% Hits@10 test accuracy in both the WN18RRv1 and NELL995v1 inductive KG completion tasks, and can accurately perform logical reasoning tasks that no existing methods can perform, to the best of our knowledge.

Authors: Jianfei Gao, Yangze Zhou, Bruno Ribeiro.

2023-02-02

Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling

  • The ensembles are created via sets of fixed dropout masks, making them less expensive than creating separate NF models
  • In these experiments, we setup an active learning framework and evaluate each model's capability at measuring aleatoric and epistemic uncertainty.

In this work, we demonstrate how to reliably estimate epistemic uncertainty while maintaining the flexibility needed to capture complicated aleatoric distributions. To this end, we propose an ensemble of Normalizing Flows (NF), which are state-of-the-art in modeling aleatoric uncertainty. The ensembles are created via sets of fixed dropout masks, making them less expensive than creating separate NF models. We demonstrate how to leverage the unique structure of NFs, base distributions, to estimate aleatoric uncertainty without relying on samples, provide a comprehensive set of baselines, and derive unbiased estimates for differential entropy. The methods were applied to a variety of experiments, commonly used to benchmark aleatoric and epistemic uncertainty estimation: 1D sinusoidal data, 2D windy grid-world ($\it{Wet Chicken}$), $\it{Pendulum}$, and $\it{Hopper}$. In these experiments, we setup an active learning framework and evaluate each model's capability at measuring aleatoric and epistemic uncertainty. The results show the advantages of using NF ensembles in capturing complicated aleatoric while maintaining accurate epistemic uncertainty estimates.

Authors: Lucas Berry, David Meger.

2023-02-02

Invariant KAM tori around annular vortex patches for 2D Euler equations

  • These structures are captured close to any annulus provided that its modulus belongs to a massive Borel set
  • Compared to the scalar case, some technical issues emerge due to the interaction between the interfaces.
We construct time quasi-periodic vortex patch solutions with one hole for the planar Euler equations. These structures are captured close to any annulus provided that its modulus belongs to a massive Borel set. The proof is based on Nash-Moser scheme and KAM theory applied with a Hamiltonian system governing the radial deformations of the patch. Compared to the scalar case, some technical issues emerge due to the interaction between the interfaces. One of them is related to a new small divisor problem in the second order Melnikov non-resonances condition coming from the transport equations advected with different velocities.

Authors: Zineb Hassainia, Taoufik Hmidi, Emeric Roulley.

2023-02-02

Bayesian Optimization of Multiple Objectives with Different Latencies

  • In some cases, it is possible to evaluate the objectives separately, and a different latency or evaluation cost can be associated with each objective
  • We prove consistency of the algorithm and show empirically that it significantly outperforms a benchmark algorithm which always evaluates both objectives.

Multi-objective Bayesian optimization aims to find the Pareto front of optimal trade-offs between a set of expensive objectives while collecting as few samples as possible. In some cases, it is possible to evaluate the objectives separately, and a different latency or evaluation cost can be associated with each objective. This presents an opportunity to learn the Pareto front faster by evaluating the cheaper objectives more frequently. We propose a scalarization based knowledge gradient acquisition function which accounts for the different evaluation costs of the objectives. We prove consistency of the algorithm and show empirically that it significantly outperforms a benchmark algorithm which always evaluates both objectives.

Authors: Jack M. Buckingham, Sebastian Rojas Gonzalez, Juergen Branke.

2023-02-02

High-Resolution Short-Circuit Fault Localization in a Multi-Layer Integrated Circuit using a Quantum Diamond Microscope

  • After quantifying the performance by detecting short-circuit faults in a multi-layer silicon die, we assess how a QDM would detect faults in a heterogeneously integrated (HI) die stack
  • This work establishes QDM-based magnetic imaging as a competitive technique for electronics FA, offering high spatial resolution, high sensitivity, and robust instrumentation
  • We anticipate these advantages to be especially useful for finding faults deep within chip-stack ICs with many metal layers, optically-opaque layers, or optically-scattering layers.
As integrated circuit (IC) geometry and packaging become more sophisticated with ongoing fabrication and design innovations, the electrical engineering community needs increasingly-powerful failure analysis (FA) methods to meet the growing troubleshooting challenges of multi-layer (with multiple metal layers) and multi-chip components. In this work, we investigate a new electronics FA method using a quantum diamond microscope (QDM) to image the magnetic fields from short-circuit faults. After quantifying the performance by detecting short-circuit faults in a multi-layer silicon die, we assess how a QDM would detect faults in a heterogeneously integrated (HI) die stack. This work establishes QDM-based magnetic imaging as a competitive technique for electronics FA, offering high spatial resolution, high sensitivity, and robust instrumentation. We anticipate these advantages to be especially useful for finding faults deep within chip-stack ICs with many metal layers, optically-opaque layers, or optically-scattering layers.

Authors: P. Kehayias, J. Walraven, A. L. Rodarte, A. M. Mounce.

2023-02-02

What Language Reveals about Perception: Distilling Psychophysical Knowledge from Large Language Models

  • Understanding the extent to which the perceptual world can be recovered from language is a fundamental problem in cognitive science
  • We also explore meaningful divergences between LLM and human representations.

Understanding the extent to which the perceptual world can be recovered from language is a fundamental problem in cognitive science. We reformulate this problem as that of distilling psychophysical information from text and show how this can be done by combining large language models (LLMs) with a classic psychophysical method based on similarity judgments. Specifically, we use the prompt auto-completion functionality of GPT3, a state-of-the-art LLM, to elicit similarity scores between stimuli and then apply multidimensional scaling to uncover their underlying psychological space. We test our approach on six perceptual domains and show that the elicited judgments strongly correlate with human data and successfully recover well-known psychophysical structures such as the color wheel and pitch spiral. We also explore meaningful divergences between LLM and human representations. Our work showcases how combining state-of-the-art machine models with well-known cognitive paradigms can shed new light on fundamental questions in perception and language research.

Authors: Raja Marjieh, Ilia Sucholutsky, Pol van Rijn, Nori Jacoby, Thomas L. Griffiths.

2023-02-02

The Non-Axisymmetric Influence: Radius and Angle-Dependent Trends in a Barred Galaxy

  • Many disc galaxies host galactic bars, which exert time-dependent, non-axisymmetric forces that can alter the orbits of stars
  • We find that the bar induces both azimuth angle- and radius-dependent trends in the median distance that stars have travelled to enter a given annulus
  • In the inner zone, stars generally originated at larger radii and their orbits evolved inwards
  • Stars in the outer zone likely originated at smaller radii and their orbits evolved outwards
  • In the intermediate zone, there is no net inwards or outwards evolution of orbits.
Many disc galaxies host galactic bars, which exert time-dependent, non-axisymmetric forces that can alter the orbits of stars. There should be both angle and radius-dependence in the resulting radial re-arrangement of stars ('radial mixing') due to a bar; we present here novel results and trends through analysis of the joint impact of these factors. We use an N-body simulation to investigate the changes in the radial locations of star particles in a disc after a bar forms by quantifying the change in orbital radii in a series of annuli at different times post bar-formation. We find that the bar induces both azimuth angle- and radius-dependent trends in the median distance that stars have travelled to enter a given annulus. Angle-dependent trends are present at all radii we consider, and the radius-dependent trends roughly divide the disc into three 'zones'. In the inner zone, stars generally originated at larger radii and their orbits evolved inwards. Stars in the outer zone likely originated at smaller radii and their orbits evolved outwards. In the intermediate zone, there is no net inwards or outwards evolution of orbits. We adopt a simple radius-dependent initial metallicity gradient and discuss recent observational evidence for angle-dependent stellar metallicity variations in the Milky Way in the context of this toy model. We briefly comment on the possibility of using observed angle-dependent metallicity trends to learn about the initial metallicity gradient(s) and the radial re-arrangement that occurred in the disc.

Authors: Carrie Filion, Rachel L. McClure, Martin D. Weinberg, Elena D'Onghia, Kathryne J. Daniel.

2023-02-02

More results on the $z$-chromatic number of graphs

  • Denote the Grundy and {\rm b}-chromatic number of $G$ by $\Gamma(G)$ and ${\rm b}(G)$, respectively
  • The $z$-coloring is an improvement over both the Grundy and b-coloring of graphs
  • We show that acyclic graphs are $z$-monotonic and $z$-continuous.

By a $z$-coloring of a graph $G$ we mean any proper vertex coloring consisting of the color classes $C_1, \ldots, C_k$ such that $(i)$ for any two colors $i$ and $j$ with $1 \leq i < j \leq k$, any vertex of color $j$ is adjacent to a vertex of color $i$, $(ii)$ there exists a set $\{u_1, \ldots, u_k\}$ of vertices of $G$ such that $u_j \in C_j$ for any $j \in \{1, \ldots, k\}$ and $u_k$ is adjacent to $u_j$ for each $1 \leq j \leq k$ with $j \not=k$, and $(iii)$ for each $i$ and $j$ with $i \not= j$, the vertex $u_j$ has a neighbor in $C_i$. Denote by $z(G)$ the maximum number of colors used in any $z$-coloring of $G$. Denote the Grundy and {\rm b}-chromatic number of $G$ by $\Gamma(G)$ and ${\rm b}(G)$, respectively. The $z$-coloring is an improvement over both the Grundy and b-coloring of graphs. We prove that $z(G)$ is much better than $\min\{\Gamma(G), {\rm b}(G)\}$ for infinitely many graphs $G$ by obtaining an infinite sequence $\{G_n\}_{n=3}^{\infty}$ of graphs such that $z(G_n)=n$ but $\Gamma(G_n)={\rm b}(G_n)=2n-1$ for each $n\geq 3$. We show that acyclic graphs are $z$-monotonic and $z$-continuous. Then it is proved that to decide whether $z(G)=\Delta(G)+1$ is $NP$-complete even for bipartite graphs $G$. We finally prove that to recognize graphs $G$ satisfying $z(G)=\chi(G)$ is $coNP$-complete, improving a previous result for the Grundy number.

Authors: Abbas Khaleghi, Manouchehr Zaker.