Search

ATOMKI nuclear anomaly has suggested a new BSM (Beyond the Standard Model) boson with mass $\sim17$ MeV emitted from excited nuclei and quickly decays into a pair of $e^+e^-$. In order to search for the new particle, we propose a new approach that utilizes the ongoing Coherent CAPTAIN-Mills (CCM) 10-ton LAr (liquid argon) detectors. The neutrons from the Lujan target can scatter inelastically by the PMT glass in the CCM detector can produce the new boson which solves the ATOMKI anomaly. The new boson can be detected from its decay to a $e^+e^-$ pair. We find that CCM probe a large area of the anomaly allowed parameter space. We also show the prediction for a 100 ton LAr detector., Comment: 6 pages, 3 figures

The piecewise-stationary bandit problem is an important variant of the multi-armed bandit problem that further considers abrupt changes in the reward distributions. The main theme of the problem is the trade-off between exploration for detecting environment changes and exploitation of traditional bandit algorithms. While this problem has been extensively investigated, existing works either assume knowledge about the number of change points $M$ or require extremely high computational complexity. In this work, we revisit the piecewise-stationary bandit problem from a minimalist perspective. We propose a novel and generic exploration mechanism, called diminishing exploration, which eliminates the need for knowledge about $M$ and can be used in conjunction with an existing change detection-based algorithm to achieve near-optimal regret scaling. Simulation results show that despite oblivious of $M$, equipping existing algorithms with the proposed diminishing exploration generally achieves better empirical regret than the traditional uniform exploration.

Kerr-Newman black holes in a de Sitter space have the limit of rotating Nariai black holes with the near-horizon geometry of a warped ${\rm dS}_3 \times {\rm S}^1/Z_2$ when the black hole horizon and the cosmological horizon coincide or approach close to each other. We study the effect of rotation on the emission of charges in the near-extremal rotating charged Nariai black hole and compare it to those from the near-extremal Nariai black hole and near-extremal Kerr-Newman black hole in de Sitter space. The emission has an exponential amplification for charges with high energy and becomes catastrophic when the two horizons are very close to each together. The angular momentum of black holes decreases the mean number of charges by a factor not by an order. We observe a catastrophic emission of boson condensation for charges with the effective energy equal to the chemical potential in the spacelike outer region of the cosmological horizon. Further, the rotating charged Nariai black holes can evolve into singular spacetimes with a naked singularity by the Schwinger pair production., Comment: 11 pages, 6 figures. arXiv admin note: text overlap with arXiv:2309.00218

Recent advancements in multimodal large language models (LLMs) have shown their potential in various domains, especially concept reasoning. Despite these developments, applications in understanding 3D environments remain limited. This paper introduces Reason3D, a novel LLM designed for comprehensive 3D understanding. Reason3D takes point cloud data and text prompts as input to produce textual responses and segmentation masks, facilitating advanced tasks like 3D reasoning segmentation, hierarchical searching, express referring, and question answering with detailed mask outputs. Specifically, we propose a hierarchical mask decoder to locate small objects within expansive scenes. This decoder initially generates a coarse location estimate covering the object's general area. This foundational estimation facilitates a detailed, coarse-to-fine segmentation strategy that significantly enhances the precision of object identification and segmentation. Experiments validate that Reason3D achieves remarkable results on large-scale ScanNet and Matterport3D datasets for 3D express referring, 3D question answering, and 3D reasoning segmentation tasks. Code and models are available at: https://github.com/KuanchihHuang/Reason3D., Comment: Project Page: https://KuanchihHuang.github.io/project/reason3d

In this paper, the heterogeneous distributed quickest change detection (HetDQCD) with 1-bit non-anonymous feedback is studied. The concept of syndromes is introduced and the family of syndrome-based fusion rules is proposed, which encompasses all deterministic fusion rules as special cases. Through the Hasse diagram of syndromes, upper and lower bounds on the second-order performance of expected detection delay as a function of average run length to false alarm are provided. An interesting instance, the weighted voting rule previously proposed in our prior work, is then revisited, for which an efficient pruning method for breadth-first search in the Hasse diagram is proposed to analyze the performance. This in turn assists in the design of the weight threshold in the weighted voting rule. Simulation results corroborate that our analysis is instrumental in identifying a proper design for the weighted voting rule, demonstrating consistent superiority over both the anonymous voting rule and the group selection rule in HetDQCD.

This paper explores differentially-private federated learning (FL) across time-varying databases, delving into a nuanced three-way tradeoff involving age, accuracy, and differential privacy (DP). Emphasizing the potential advantages of scheduling, we propose an optimization problem aimed at meeting DP requirements while minimizing the loss difference between the aggregated model and the model obtained without DP constraints. To harness the benefits of scheduling, we introduce an age-dependent upper bound on the loss, leading to the development of an age-aware scheduling design. Simulation results underscore the superior performance of our proposed scheme compared to FL with classic DP, which does not consider scheduling as a design factor. This research contributes insights into the interplay of age, accuracy, and DP in federated learning, with practical implications for scheduling strategies., Comment: Simulation parameters updated. Paper accepted for presentation at the 2024 IEEE International Symposium on Information Theory (ISIT 2024)

We consider the nuclear absorption of dark matter as an alternative to the typical indirect detection search channels of dark matter decay or annihilation. In this scenario, an atomic nucleus transitions to an excited state by absorbing a pseudoscalar dark matter particle and promptly emits a photon as it transitions back to its ground state. The nuclear excitation of carbon and oxygen in the Galactic Center would produce a discrete photon spectrum in the $\mathcal{O}(10)$ MeV range that could be detected by gamma-ray telescopes. Using the \texttt{BIGSTICK} large-scale shell-model code, we calculate the excitation energies of carbon and oxygen. We constrain the dark matter-nucleus coupling for current COMPTEL data, and provide projections for future experiments AMEGO-X, e-ASTROGAM, and GRAMS for dark matter masses from $\sim$ 10 to 30 MeV. We find the excitation process to be very sensitive to the dark matter mass and find that the future experiments considered would improve constraints on the dark matter-nucleus coupling within an order of magnitude., Comment: 7 pages, 4 figures, 1 table

This study introduces a novel approach to enhance communication networks in the cislunar space by leveraging Reconfigurable Intelligent Surfaces (RIS). Using the ability of RIS to dynamically control electromagnetic waves, this paper tackles the challenges of signal attenuation, directivity, and divergence in cislunar missions, primarily caused by immense distances and that Earth-based station transmitters do not always face the Moon. A new optimization problem is formulated, whose objective is to maximize the received signal-to-noise ratio (SNR) for Earth-to-Moon communications. We derive a closed-form solution to the problem of determining the optimal RIS phase shift configuration based on the effective area of the RIS. Through extensive simulations, this paper demonstrates how optimal adjustments in RIS phase shifts can significantly enhance signal integrity, hinting at the substantial potential of RIS technology to revolutionize long-distance cislunar communication., Comment: The submission includes 6 pages in double-column format, with 6 figures, and has been submitted to the IEEE Globecom 2024 conference

Our goal in this paper is to prove the global existence of a classical solution for the isentropic nozzle flow. Regarding this problem, there exist some global existence theorems of weak solutions. However, that of classical solutions does not have much attention until now. When we consider the present problem, the main difficulty is to obtain the uniform bound of solutions and their derivatives. To solve this, we introduce an invariant region depending on the space variable and a functional satisfying the Riccati equation along the characteristic lines.

We propose a new approach to search for light dark matter (DM), with keV-GeV mass, via inelastic nucleus scattering at large-volume neutrino detectors such as Borexino, DUNE, Super-K, Hyper-K, and JUNO. The approach uses inelastic nuclear scattering of cosmic-ray boosted DM, enabling a low background search for DM in these experiments. Large neutrino detectors, with higher thresholds than dark matter detectors, can be used, since the nuclear deexcitation lines are O(10) MeV. Using a hadrophilic dark-gauge-boson-portal model as a benchmark, we show that the nuclear inelastic channels generally provide better sensitivity than the elastic scattering for a large region of light DM parameter space., Comment: 8 pages, 3 figures

Recent temporal LiDAR-based 3D object detectors achieve promising performance based on the two-stage proposal-based approach. They generate 3D box candidates from the first-stage dense detector, followed by different temporal aggregation methods. However, these approaches require per-frame objects or whole point clouds, posing challenges related to memory bank utilization. Moreover, point clouds and trajectory features are combined solely based on concatenation, which may neglect effective interactions between them. In this paper, we propose a point-trajectory transformer with long short-term memory for efficient temporal 3D object detection. To this end, we only utilize point clouds of current-frame objects and their historical trajectories as input to minimize the memory bank storage requirement. Furthermore, we introduce modules to encode trajectory features, focusing on long short-term and future-aware perspectives, and then effectively aggregate them with point cloud features. We conduct extensive experiments on the large-scale Waymo dataset to demonstrate that our approach performs well against state-of-the-art methods. Code and models will be made publicly available at https://github.com/kuanchihhuang/PTT., Comment: Accepted to CVPR 2024. Project page: https://github.com/kuanchihhuang/PTT

Weakly supervised 3D object detection aims to learn a 3D detector with lower annotation cost, e.g., 2D labels. Unlike prior work which still relies on few accurate 3D annotations, we propose a framework to study how to leverage constraints between 2D and 3D domains without requiring any 3D labels. Specifically, we employ visual data from three perspectives to establish connections between 2D and 3D domains. First, we design a feature-level constraint to align LiDAR and image features based on object-aware regions. Second, the output-level constraint is developed to enforce the overlap between 2D and projected 3D box estimations. Finally, the training-level constraint is utilized by producing accurate and consistent 3D pseudo-labels that align with the visual data. We conduct extensive experiments on the KITTI dataset to validate the effectiveness of the proposed three constraints. Without using any 3D labels, our method achieves favorable performance against state-of-the-art approaches and is competitive with the method that uses 500-frame 3D annotations. Code will be made publicly available at https://github.com/kuanchihhuang/VG-W3D., Comment: Accepted by ECCV'24. Project page: https://github.com/kuanchihhuang/VG-W3D

Stopped-pion experiments that measure coherent elastic neutrino-nucleus scattering (CE$\nu$NS) are sensitive to sterile neutrinos via disappearance. Using timing and energy spectra to perform flavor decomposition, we show that the delayed electron neutrino component provides an independent test of short-baseline anomalies that hint at $\sim$ eV-mass sterile neutrinos. Dedicated experiments will be sensitive to nearly the entire sterile neutrino parameter space consistent with short-baseline data.

Using both the in-out formalism and the monodromy method, we study the emission of charges from near-extremal charged Nariai black holes with the black hole and cosmological horizons close to each other, whose near-horizon geometry is $\mathrm{dS}_2 \times \mathrm{S}^2$. The emission becomes catastrophic for a charge with energy greater than its chemical potential, whose leading exponential factor increases inversely proportional to the separation of two horizons. This implies that near-extremal Nariai black holes with large charges quickly evaporate dominantly through the charge emission and evolve to black holes with a naked singularity, in contrast to near-extremal RN-dS black holes that have the Breitenlohner-Friedman bound below which they become stable against Hawking radiation and Schwinger effect of charge emission. The near-extremal Nariai black holes with small charges, which are close to near-extremal Schwarzschild-dS black holes, emit dominantly charge-neutral particles and evolve to black holes with increasing charge to mass ratio. We illuminate the origin of the catastrophic emission in the phase-integral formulation and monodromy method by comparing near-extremal charged Nariai black holes with near-extremal RN-dS black holes., Comment: revised version including corrections of mistakes and more physical discussions

Recent advances of monocular 3D object detection facilitate the 3D multi-object tracking task based on low-cost camera sensors. In this paper, we find that the motion cue of objects along different time frames is critical in 3D multi-object tracking, which is less explored in existing monocular-based approaches. In this paper, we propose a motion-aware framework for monocular 3D MOT. To this end, we propose MoMA-M3T, a framework that mainly consists of three motion-aware components. First, we represent the possible movement of an object related to all object tracklets in the feature space as its motion features. Then, we further model the historical object tracklet along the time frame in a spatial-temporal perspective via a motion transformer. Finally, we propose a motion-aware matching module to associate historical object tracklets and current observations as final tracking results. We conduct extensive experiments on the nuScenes and KITTI datasets to demonstrate that our MoMA-M3T achieves competitive performance against state-of-the-art methods. Moreover, the proposed tracker is flexible and can be easily plugged into existing image-based 3D object detectors without re-training. Code and models are available at https://github.com/kuanchihhuang/MoMA-M3T., Comment: Accepted by ICCV 2023. Code is available at https://github.com/kuanchihhuang/MoMA-M3T

The problem of enabling the coexistence of heterogeneous services, e.g., different ultra-reliable low-latency communications (URLLC) services and/or enhanced mobile broadband (eMBB) services, in the uplink is studied. Each service has its own error probability and blocklength constraints and the longer transmission block suffers from heterogeneous interference. Due to the latency concern, the decoding of URLLC messages cannot leverage successive interference cancellation (SIC) and should always be performed before the decoding of eMBB messages. This can significantly degrade the achievable rates of URLLC users when the interference from other users is strong. To overcome this issue, we propose a new transmission scheme based on discrete signaling and treating interference as noise decoding, i.e., without SIC. Guided by the deterministic model, we provide a systematic way to construct discrete signaling for handling heterogeneous interference effectively. We demonstrate theoretically and numerically that the proposed scheme can perform close to the benchmark scheme based on capacity-achieving Gaussian signaling with the assumption of perfect SIC., Comment: 7 pages, accepted for presentation at IEEE Global Communications Conference (GLOBECOM) 2023

In this paper, we study the transmission strategy of a ground-based beyond diagonal reconfigurable intelligent surface (BD-RIS), a.k.a RIS 2.0, in a network where multiple unmanned aerial vehicles (UAVs) simultaneously transmit signals to the respective groups of users. It is assumed that each group is assigned subcarriers orthogonal to those assigned to other groups and rate splitting multiple access (RSMA) is adopted within each group. A corresponding mixed integer nonlinear programming problem (MINLP) is formulated, which aims to jointly optimize 1) allocation of BD-RIS elements to groups, 2) BD-RIS phase rotations, 3) rate allocation in RSMA, and 4) precoders. To solve the problem, we propose using generalized benders decomposition (GBD) augmented with a manifold-based algorithm. GBD splits the MINLP problem into two sub-problems, namely the primal and the relaxed master problem, which are solved alternately and iteratively. In the primal problem, we apply block coordinate descent (BCD) to manage the coupling of variables effectively. Moreover, we recognize the manifold structure in the phase rotation constraint of BD-RIS, enabling the Riemannian conjugate gradient (RCG). Simulation results demonstrate the effectiveness of the proposed approach in maximizing spectral efficiency.

Age of information (AoI) is an effective performance metric measuring the freshness of information and is particularly suitable for applications involving status update. In this paper, using the age violation probability as the metric, scheduling for heterogeneous multi-source systems is studied. Two queueing disciplines, namely the infinite packet queueing discipline and the single packet queueing discipline, are considered for scheduling packets within each source. A generalized round-robin (GRR) scheduling policy is then proposed to schedule the sources. Bounds on the exponential decay rate of the age violation probability for the proposed GRR scheduling policy under each queueing discipline are rigorously analyzed. Simulation results are provided, which show that the proposed GRR scheduling policy can efficiently serve many sources with heterogeneous arrivals and that our bounds can capture the true decay rate quite accurately. When specialized to the homogeneous source setting, the analysis concretizes the common belief that the single packet queueing discipline has a better AoI performance than the infinite packet queueing discipline. Moreover, simulations on this special case reveals that under the proposed scheduling policy, the two disciplines would have similar asymptotic performance when the inter-arrival time is much larger than the total transmission time., Comment: 32 pages, 11 figures. arXiv admin note: text overlap with arXiv:2206.04303

Here we present world-leading sensitivity to light ($< 170$ MeV) dark matter (DM) using beam-dump experiments. Dark sector particles produced during pion decay at accelerator beam-dumps can be detected via scattering in neutrino detectors. The decay of nuclei excited by the inelastic scattering of DM is an unexploited channel which has significantly better sensitivity than similar searches using the elastic scattering channel. We show that this channel is a powerful probe of DM by demonstrating sensitivity to the thermal relic abundance benchmark in a scalar DM dark-photon portal model. This is achieved through the use of existing data, obtained by the KARMEN experiment over two decades ago, which allow us to set world-leading constraints on this model over a wide mass range. With experimental improvements planned for the future, this technique will be able to probe the thermal relic benchmark for fermionic DM across a wide mass range., Comment: 5 pages, 4 figures. V2 updated with bounds from KARMEN and projections for PIP2BD. V3 as accepted by PRL

A private information retrieval (PIR) scheme allows a client to retrieve a data item $x_i$ among $n$ items $x_1,x_2,\ldots,x_n$ from $k$ servers, without revealing what $i$ is even when $t < k$ servers collude and try to learn $i$. Such a PIR scheme is said to be $t$-private. A PIR scheme is $v$-verifiable if the client can verify the correctness of the retrieved $x_i$ even when $v \leq k$ servers collude and try to fool the client by sending manipulated data. Most of the previous works in the literature on PIR assumed that $v < k$, leaving the case of all-colluding servers open. We propose a generic construction that combines a linear map commitment (LMC) and an arbitrary linear PIR scheme to produce a $k$-verifiable PIR scheme, termed a committed PIR scheme. Such a scheme guarantees that even in the worst scenario, when all servers are under the control of an attacker, although the privacy is unavoidably lost, the client won't be fooled into accepting an incorrect $x_i$. We demonstrate the practicality of our proposal by implementing the committed PIR schemes based on the Lai-Malavolta LMC and three well-known PIR schemes using the GMP library and blst, the current fastest C library for elliptic curve pairings., Comment: Accepted at ESORICS 2023

In this paper, we consider the downlink broadcast channel under heterogenous blocklength constraints, where each user experiences different interference statistics across its received symbols. Different from the homogeneous blocklength case, the strong users with short blocklength transmitted symbol blocks usually cannot wait to receive the entire transmission frame and perform successive interference cancellation (SIC) owing to their stringent latency requirements. Even if SIC is feasible, it may not be perfect under finite blocklength constraints. To cope with the heterogeneity in latency and reliability requirements, we propose a practical downlink transmission scheme with discrete signaling and single-user decoding, i.e., without SIC. In addition, we derive the finite blocklength achievable rate and use it for guiding the design of channel coding and modulations. Both achievable rate and error probability simulation show that the proposed scheme can operate close to the benchmark scheme which assumes capacity-achieving signaling and perfect SIC., Comment: 7 pages, 1 figure, accepted for presentation at IEEE ICC 2023. arXiv admin note: substantial text overlap with arXiv:2212.01736

The problem of designing downlink transmission schemes for supporting heterogeneous ultra-reliable low-latency communications (URLLC) and/or with other types of services is investigated. We consider the broadcast channel, where the base station sends superimposed signals to multiple users. Under heterogeneous blocklength constraints, strong users who are URLLC users cannot wait to receive the entire transmission frame and perform successive interference cancellation (SIC) due to stringent latency requirements, in contrast to the conventional infinite blocklength cases. Even if SIC is feasible, SIC may be imperfect under finite blocklength constraints. To cope with the heterogeneity in latency and reliability requirements, we propose a practical downlink transmission scheme with discrete signaling and single-user decoding (SUD), i.e., without SIC. We carefully design the discrete input distributions to enable efficient SUD by exploiting the structural interference. Furthermore, we derive the second-order achievable rate under heterogenous blocklength and error probability constraints and use it to guide the design of channel coding and modulations. It is shown that in terms of achievable rate under short blocklength, the proposed scheme with regular quadrature amplitude modulations and SUD can operate extremely close to the benchmark schemes that assume perfect SIC with Gaussian signaling., Comment: 16 pages, 7 figures, accepted by IEEE Journal on Selected Areas in Communications

Searches for axion-like particles (ALPs) are motivated by the strong CP problem in particle physics and by unexplained dark matter in astrophysics. In this letter, we discuss novel ALP searches using monoenergetic nuclear de-excitation photons from a beam dump, using IsoDAR as an example. We show that IsoDAR can set limits that close a gap in traditional QCD axion searches using the ALP-photon coupling, as well as provide sensitivity to large regions of new parameter space in models where ALPs couple to nucleons and electrons. We also show how isotope decay-at-rest experiments may be designed to improve potential ALP production and optimize detection sensitivity., Comment: 8 pages including references, 4 figures, one table, 8 equations, PRL format

Neutrinos with energy of order 10~MeV, such as from pion decay-at-rest sources, are an invaluable tool for studying low-energy neutrino interactions with nuclei -- previously enabling the first measurement of coherent elastic neutrino-nucleus scattering. Beyond elastic scattering, neutrinos and dark matter in this energy range also excite nuclei to its low-lying nuclear states, providing an additional physics channel. Here, we consider neutral-current inelastic neutrino-nucleus and dark matter(DM)-nucleus scattering off $^{40}$Ar, $^{133}$Cs, and $^{127}$I nuclei that are relevant to a number of low-threshold neutrino experiments at pion decay-at-rest facilities. We carry out large scale nuclear shell model calculations of the inelastic cross sections considering the full set of electroweak multipole operators. Our results demonstrate that Gamow-Teller transitions provide the dominant contribution to the cross section and that the long-wavelength limit provides a reasonable approximation to the total cross section for neutrino sources. We show that future experiments will be sensitive to this channel and thus these results provide additional neutrino and DM scattering channels to explore at pion decay-at-rest facilities., Comment: 16 pages, 12 figures, published version

Age of information (AoI) is an effective performance metric measuring the freshness of information and is popular for applications involving status update. Most of the existing works have adopted average AoI as the metric, which cannot provide strict performance guarantees. In this work, the outage probability of the peak AoI exceeding a given threshold is analyzed in a multi-source system under round robin scheduling. Two queueing disciplines are considered, namely the first-come-first-serve (FCFS) queue and the single packet queue. For FCFS, upper and lower bounds on the outage probability are derived which coincides asymptotically, characterizing its true scaling. For the single packet queue, an upper bound is derived whose effectiveness is validated by the simulation results. The analysis concretizes the common belief that single packet queueing has a better AoI performance than FCFS. Moreover, it also reveals that the two disciplines would have similar asymptotic performance when the inter-arrival time is much larger than the total transmission time.

We present a simple but novel hybrid approach to hyperspectral data cube reconstruction from computed tomography imaging spectrometry (CTIS) images that sequentially combines neural networks and the iterative Expectation Maximization (EM) algorithm. We train and test the ability of the method to reconstruct data cubes of $100\times100\times25$ and $100\times100\times100$ voxels, corresponding to 25 and 100 spectral channels, from simulated CTIS images generated by our CTIS simulator. The hybrid approach utilizes the inherent strength of the Convolutional Neural Network (CNN) with regard to noise and its ability to yield consistent reconstructions and make use of the EM algorithm's ability to generalize to spectral images of any object without training. The hybrid approach achieves better performance than both the CNNs and EM alone for seen (included in CNN training) and unseen (excluded from CNN training) cubes for both the 25- and 100-channel cases. For the 25 spectral channels, the improvements from CNN to the hybrid model (CNN + EM) in terms of the mean-squared errors are between 14-26%. For 100 spectral channels, the improvements between 19-40% are attained with the largest improvement of 40% for the unseen data, to which the CNNs are not exposed during the training., Comment: 36 pages, 13 figures and 2 tables. Supplemental material: 21 pages and 14 figures. v2: Clarifications added, analyses and argumentation updated

A Batch Private Information Retrieval (batch-PIR) scheme allows a client to retrieve multiple data items from a database without revealing them to the storage server(s). Most existing approaches for batch-PIR are based on batch codes, in particular, probabilistic batch codes (PBC) (Angel et al. S&P'18), which incur large storage overheads. In this work, we show that \textit{zero} storage overhead is achievable for tree-shaped databases. In particular, we develop TreePIR, a novel approach tailored made for private retrieval of the set of nodes along an arbitrary root-to-leaf path in a Merkle tree with no storage redundancy. This type of trees has been widely implemented in many real-world systems such as Amazon DynamoDB, Google's Certificate Transparency, and blockchains. Tree nodes along a root-to-leaf path forms the well-known Merkle proof. TreePIR, which employs a novel tree coloring, outperforms PBC, a fundamental component in state-of-the-art batch-PIR schemes (Angel et al. S&P'18, Mughees-Ren S&P'23, Liu et al. S&P'24), in all metrics, achieving $3\times$ lower total storage and $1.5$-$2\times$ lower computation and communication costs. Most notably, TreePIR has $8$-$160\times$ lower setup time and its polylog-complexity indexing algorithm is $19$-$160\times$ faster than PBC for trees of $2^{10}$-$2^{24}$ leaves., Comment: 25 pages

This paper introduces CO3 -- an algorithm for communication-efficient federated Deep Neural Network (DNN) training. CO3 takes its name from three processing applied which reduce the communication load when transmitting the local DNN gradients from the remote users to the Parameter Server. Namely: (i) gradient quantization through floating-point conversion, (ii) lossless compression of the quantized gradient, and (iii) quantization error correction. We carefully design each of the steps above to assure good training performance under a constraint on the communication rate. In particular, in steps (i) and (ii), we adopt the assumption that DNN gradients are distributed according to a generalized normal distribution, which is validated numerically in the paper. For step (iii), we utilize an error feedback with memory decay mechanism to correct the quantization error introduced in step (i). We argue that the memory decay coefficient, similarly to the learning rate, can be optimally tuned to improve convergence. A rigorous convergence analysis of the proposed CO3 with SGD is provided. Moreover, with extensive simulations, we show that CO3 offers improved performance when compared with existing gradient compression schemes in the literature which employ sketching and non-uniform quantization of the local gradients., Comment: arXiv admin note: substantial text overlap with arXiv:2203.09044

Monocular 3D object detection is an important yet challenging task in autonomous driving. Some existing methods leverage depth information from an off-the-shelf depth estimator to assist 3D detection, but suffer from the additional computational burden and achieve limited performance caused by inaccurate depth priors. To alleviate this, we propose MonoDTR, a novel end-to-end depth-aware transformer network for monocular 3D object detection. It mainly consists of two components: (1) the Depth-Aware Feature Enhancement (DFE) module that implicitly learns depth-aware features with auxiliary supervision without requiring extra computation, and (2) the Depth-Aware Transformer (DTR) module that globally integrates context- and depth-aware features. Moreover, different from conventional pixel-wise positional encodings, we introduce a novel depth positional encoding (DPE) to inject depth positional hints into transformers. Our proposed depth-aware modules can be easily plugged into existing image-only monocular 3D object detectors to improve the performance. Extensive experiments on the KITTI dataset demonstrate that our approach outperforms previous state-of-the-art monocular-based methods and achieves real-time detection. Code is available at https://github.com/kuanchihhuang/MonoDTR, Comment: Accepted to CVPR 2022

In this paper, we introduce a novel algorithm, $\mathsf{CO}_3$, for communication-efficiency distributed Deep Neural Network (DNN) training. $\mathsf{CO}_3$ is a joint training/communication protocol, which encompasses three processing steps for the network gradients: (i) quantization through floating-point conversion, (ii) lossless compression, and (iii) error correction. These three components are crucial in the implementation of distributed DNN training over rate-constrained links. The interplay of these three steps in processing the DNN gradients is carefully balanced to yield a robust and high-performance scheme. The performance of the proposed scheme is investigated through numerical evaluations over CIFAR-10.