arXiv subjects

Ning Yan

Publications and source records attributed to Ning Yan.

25 records · Page 2Linked to original sources

arXiv2022

Theta-Resonance: A Single-Step Reinforcement Learning Method for Design Space Exploration

Given an environment (e.g., a simulator) for evaluating samples in a specified design space and a set of weighted evaluation metrics -- one can use Theta-Resonance, a single-step Markov Decision Process (MDP), to train an intelligent agent producing progressively more optimal samples. In Theta-Resonance, a neural network consumes a constant input tensor and produces a policy as a set of conditional probability density functions (PDFs) for sampling each design dimension. We specialize existing policy gradient algorithms in deep reinforcement learning (D-RL) in order to use evaluation feedback (in terms of cost, penalty or reward) to update our policy network with robust algorithmic stability and minimal design evaluations. We study multiple neural architectures (for our policy network) within the context of a simple SoC design space and propose a method of constructing synthetic space exploration problems to compare and improve design space exploration (DSE) algorithms. Although we only present categorical design spaces, we also outline how to use Theta-Resonance in order to explore continuous and mixed continuous-discrete design spaces.

cs.LG↗

arXiv2021

Fully Convolutional Scene Graph Generation

This paper presents a fully convolutional scene graph generation (FCSGG) model that detects objects and relations simultaneously. Most of the scene graph generation frameworks use a pre-trained two-stage object detector, like Faster R-CNN, and build scene graphs using bounding box features. Such pipeline usually has a large number of parameters and low inference speed. Unlike these approaches, FCSGG is a conceptually elegant and efficient bottom-up approach that encodes objects as bounding box center points, and relationships as 2D vector fields which are named as Relation Affinity Fields (RAFs). RAFs encode both semantic and spatial features, and explicitly represent the relationship between a pair of objects by the integral on a sub-region that points from subject to object. FCSGG only utilizes visual features and still generates strong results for scene graph generation. Comprehensive experiments on the Visual Genome dataset demonstrate the efficacy, efficiency, and generalizability of the proposed method. FCSGG achieves highly competitive results on recall and zero-shot recall with significantly reduced inference time.

cs.CV↗

arXiv2020

The Impact of Hole Geometry on Relative Robustness of In-Painting Networks: An Empirical Study

In-painting networks use existing pixels to generate appropriate pixels to fill "holes" placed on parts of an image. A 2-D in-painting network's input usually consists of (1) a three-channel 2-D image, and (2) an additional channel for the "holes" to be in-painted in that image. In this paper, we study the robustness of a given in-painting neural network against variations in hole geometry distributions. We observe that the robustness of an in-painting network is dependent on the probability distribution function (PDF) of the hole geometry presented to it during its training even if the underlying image dataset used (in training and testing) does not alter. We develop an experimental methodology for testing and evaluating relative robustness of in-painting networks against four different kinds of hole geometry PDFs. We examine a number of hypothesis regarding (1) the natural bias of in-painting networks to the hole distribution used for their training, (2) the underlying dataset's ability to differentiate relative robustness as hole distributions vary in a train-test (cross-comparison) grid, and (3) the impact of the directional distribution of edges in the holes and in the image dataset. We present results for L1, PSNR and SSIM quality metrics and develop a specific measure of relative in-painting robustness to be used in cross-comparison grids based on these quality metrics. (One can incorporate other quality metrics in this relative measure.) The empirical work reported here is an initial step in a broader and deeper investigation of "filling the blank" neural networks' sensitivity, robustness and regularization with respect to hole "geometry" PDFs, and it suggests further research in this domain.

cs.CV↗

arXiv2017

A Convolutional Neural Network Approach for Half-Pel Interpolation in Video Coding

Motion compensation is a fundamental technology in video coding to remove the temporal redundancy between video frames. To further improve the coding efficiency, sub-pel motion compensation has been utilized, which requires interpolation of fractional samples. The video coding standards usually adopt fixed interpolation filters that are derived from the signal processing theory. However, as video signal is not stationary, the fixed interpolation filters may turn out less efficient. Inspired by the great success of convolutional neural network (CNN) in computer vision, we propose to design a CNN-based interpolation filter (CNNIF) for video coding. Different from previous studies, one difficulty for training CNNIF is the lack of ground-truth since the fractional samples are actually not available. Our solution for this problem is to derive the "ground-truth" of fractional samples by smoothing high-resolution images, which is verified to be effective by the conducted experiments. Compared to the fixed half-pel interpolation filter for luma in High Efficiency Video Coding (HEVC), our proposed CNNIF achieves up to 3.2% and on average 0.9% BD-rate reduction under low-delay P configuration.

cs.MM↗

arXiv2016

Generating Preview Tables for Entity Graphs

Users are tapping into massive, heterogeneous entity graphs for many applications. It is challenging to select entity graphs for a particular need, given abundant datasets from many sources and the oftentimes scarce information for them. We propose methods to produce preview tables for compact presentation of important entity types and relationships in entity graphs. The preview tables assist users in attaining a quick and rough preview of the data. They can be shown in a limited display space for a user to browse and explore, before she decides to spend time and resources to fetch and investigate the complete dataset. We formulate several optimization problems that look for previews with the highest scores according to intuitive goodness measures, under various constraints on preview size and distance between preview tables. The optimization problem under distance constraint is NP-hard. We design a dynamic-programming algorithm and an Apriori-style algorithm for finding optimal previews. Results from experiments, comparison with related work and user studies demonstrated the scoring measures' accuracy and the discovery algorithms' efficiency.

cs.DB↗

arXiv2011

Supercharacters, symmetric functions in noncommuting variables, and related Hopf algebras

We identify two seemingly disparate structures: supercharacters, a useful way of doing Fourier analysis on the group of unipotent uppertriangular matrices with coefficients in a finite field, and the ring of symmetric functions in noncommuting variables. Each is a Hopf algebra and the two are isomorphic as such. This allows developments in each to be transferred. The identification suggests a rich class of examples for the emerging field of combinatorial Hopf algebras.

math.CO↗

arXiv2010

Representations of Finite Unipotent Linear Groups by the Method of Clusters

The general linear group GL(n, K) over a field K contains a particularly prominent subgroup U(n, K), consisting of all the upper triangular unipotent elements. In this paper we are interested in the case when K is the finite field F_q, and our goal is to better understand the representation theory of U(n, F_q). The complete classification of the complex irreducible representations of this group has long been known to be a difficult task. The orbit method of Kirillov, famous for its success when K has characteristic 0, is a natural source of intuition and conjectures, but in our case the relation between coadjoint orbits and complex representations is still a mystery. Here we introduce a natural variant of the orbit method, in which the central role is played by certain clusters of coadjoint orbits. This "method of clusters" leads to the construction of a subring in the representation ring of U(n, F_q) that is rich in structure but pleasantly comprehensible. The cluster method also has many of the major features one would expect from the philosophy of orbit method.

math.RT↗