arXiv subjects

Lei Yu

Publications and source records attributed to Lei Yu.

At least 271 records · Page 15Linked to original sources

arXiv2017

Exponential Strong Converse for Content Identification with Lossy Recovery

We revisit the high-dimensional content identification with lossy recovery problem (Tuncel and Gündüz, 2014) and establish an exponential strong converse theorem. As a corollary of the exponential strong converse theorem, we derive an upper bound on the joint identification-error and excess-distortion exponent for the problem. Our main results can be specialized to the biometrical identification problem~(Willems, 2003) and the content identification problem~(Tuncel, 2009) since these two problems are both special cases of the content identification with lossy recovery problem. We leverage the information spectrum method introduced by Oohama and adapt the strong converse techniques therein to be applicable to the problem at hand.

cs.IT↗

arXiv2017

Local exact one-sided boundary null controllability of entropy solutions to a class of hyperbolic systems of balance laws

We consider nxn hyperbolic systems of balance laws in one-space dimension under the assumption that all negative (resp. positive) characteristics are linearly degenerate. We prove the local exact one-sided boundary null controllability of entropy solutions to this class of systems, which generalizes the corresponding results from the case without source terms to that with source terms. In order to apply the strategy used for conservation law, we essentially modify the constructive method by introducing two different kinds of approximate solutions to system in the forward sense and to the system in the rightward (resp. leftward) sense, respectively, and we prove that their limit solutions are equivalent to some extend.

math.AP↗

arXiv2017

Automatic Streaming Segmentation of Stereo Video Using Bilateral Space

In this paper, we take advantage of binocular camera and propose an unsupervised algorithm based on semi-supervised segmentation algorithm and extracting foreground part efficiently. We creatively embed depth information into bilateral grid in the graph cut model and achieve considerable segmenting accuracy in the case of no user input. The experi- ment approves the high precision, time efficiency of our algorithm and its adaptation to complex natural scenario which is significant for practical application.

cs.CV↗

arXiv2017

The size of $3$-uniform hypergraphs with given matching number and codegree

Determine the size of $r$-graphs with given graph parameters is an interesting problem. Chvátal and Hanson (JCTB, 1976) gave a tight upper bound of the size of 2-graphs with restricted maximum degree and matching number; Khare (DM, 2014) studied the same problem for linear $3$-graphs with restricted matching number and maximum degree. In this paper, we give a tight upper bound of the size of $3$-graphs with bounded codegree and matching number.

math.CO↗

arXiv2017

Generalized Common Informations: Measuring Commonness by the Conditional Maximal Correlation

In literature, different common informations were defined by Gács and Körner, by Wyner, and by Kumar, Li, and Gamal, respectively. In this paper, we define two generalized versions of common informations, named approximate and exact information-correlation functions, by exploiting the conditional maximal correlation as a commonness or privacy measure. These two generalized common informations encompass the notions of Gács-Körner's, Wyner's, and Kumar-Li-Gamal's common informations as special cases. Furthermore, to give operational characterizations of these two generalized common informations, we also study the problems of private sources synthesis and common information extraction, and show that the information-correlation functions are equal to the minimum rates of commonness needed to ensure that some conditional maximal correlation constraints are satisfied for the centralized setting versions of these problems. As a byproduct, the conditional maximal correlation has been studied as well.

cs.IT↗

arXiv2017

Joint Source-Channel Secrecy Using Uncoded Schemes: Towards Secure Source Broadcast

This paper investigates a joint source-channel secrecy problem for the Shannon cipher broadcast system. We suppose list secrecy is applied, i.e., a wiretapper is allowed to produce a list of reconstruction sequences and the secrecy is measured by the minimum distortion over the entire list. For discrete communication cases, we propose a permutation-based uncoded scheme, which cascades a random permutation with a symbol-by-symbol mapping. Using this scheme, we derive an inner bound for the admissible region of secret key rate, list rate, wiretapper distortion, and distortions of legitimate users. For the converse part, we easily obtain an outer bound for the admissible region from an existing result. Comparing the outer bound with the inner bound shows that the proposed scheme is optimal under certain conditions. Besides, we extend the proposed scheme to the scalar and vector Gaussian communication scenarios, and characterize the corresponding performance as well. For these two cases, we also propose another uncoded scheme, orthogonal-transform-based scheme, which achieves the same performance as the permutation-based scheme. Interestingly, by introducing the random permutation or the random orthogonal transform into the traditional uncoded scheme, the proposed uncoded schemes, on one hand, provide a certain level of secrecy, and on the other hand, do not lose any performance in terms of the distortions for legitimate users.

cs.IT↗

arXiv2017

Odd induced subgraphs in graphs with treewidth at most two

A long-standing conjecture asserts that there exists a constant $c>0$ such that every graph of order $n$ without isolated vertices contains an induced subgraph of order at least $cn$ with all degrees odd. Scott (1992) proved that every graph $G$ has an induced subgraph of order at least $|V(G)|/(2χ(G))$ with all degrees odd, where $χ(G)$ is the chromatic number of $G$, this implies the conjecture for graphs with { bounded} chromatic number. But the factor $1/(2χ(G))$ seems to be not best possible, for example, Radcliffe and Scott (1995) proved $c=\frac 23$ for trees, Berman, Wang and Wargo (1997) showed that $c=\frac 25$ for graphs with maximum degree $3$, so it is interesting to determine the exact value of $c$ for special family of graphs. In this paper, we further confirm the conjecture for graphs with treewidth at most 2 with $c=\frac{2}{5}$, and the bound is best possible.

math.CO↗

arXiv2017

An algorithm of frequency estimation for multi-channel coprime sampling

In some applications of frequency estimation, it is challenging to sample at as high as the Nyquist rate due to hardware limitations. An effective solution is to use multiple sub-Nyquist channels with coprime undersampling ratios to jointly sample. In this paper, an algorithm suitable for any number of channels is proposed, which is based on subspace techniques. Numerical simulations show that the proposed algorithm has high accuracy and good robustness.

cs.IT↗

arXiv2017

Frequency Estimation of Multiple Sinusoids with Three Sub-Nyquist Channels

Frequency estimation of multiple sinusoids is significant in both theory and application. In some application scenarios, only sub-Nyquist samples are available to estimate the frequencies. A conventional approach is to sample the signals at several lower rates. In this paper, we address frequency estimation of the signals in the time domain through undersampled data. We analyze the impact of undersampling and demonstrate that three sub-Nyquist channels are generally enough to estimate the frequencies provided the undersampling ratios are pairwise coprime. We deduce the condition that leads to the failure of resolving frequency ambiguity when two coprime undersampling channels are utilized. When three-channel sub-Nyquist samples are used jointly, the frequencies can be determined uniquely and the correct frequencies are estimated. Numerical experiments verify the correctness of our analysis and conclusion.

cs.IT↗

arXiv2017

The Neural Noisy Channel

We formulate sequence to sequence transduction as a noisy channel decoding problem and use recurrent neural networks to parameterise the source and channel models. Unlike direct models which can suffer from explaining-away effects during training, noisy channel models must produce outputs that explain their inputs, and their component models can be trained with not only paired training samples but also unpaired samples from the marginal output distribution. Using a latent variable to control how much of the conditioning sequence the channel model needs to read in order to generate a subsequent symbol, we obtain a tractable and effective beam search decoder. Experimental results on abstractive sentence summarisation, morphological inflection, and machine translation show that noisy channel models outperform direct models, and that they significantly benefit from increased amounts of unpaired output data that direct models cannot easily use.

cs.CL↗

arXiv2017

Source-Channel Secrecy for Shannon Cipher System

Recently, a secrecy measure based on list-reconstruction has been proposed [2], in which a wiretapper is allowed to produce a list of $2^{mR_{L}}$ reconstruction sequences and the secrecy is measured by the minimum distortion over the entire list. In this paper, we show that this list secrecy problem is equivalent to the one with secrecy measured by a new quantity \emph{lossy-equivocation}, which is proven to be the minimum optimistic 1-achievable source coding rate (the minimum coding rate needed to reconstruct the source within target distortion with positive probability for \emph{infinitely many blocklengths}) of the source with the wiretapped signal as two-sided information, and also can be seen as a lossy extension of conventional equivocation. Upon this (or list) secrecy measure, we study source-channel secrecy problem in the discrete memoryless Shannon cipher system with \emph{noisy} wiretap channel. Two inner bounds and an outer bound on the achievable region of secret key rate, list rate, wiretapper distortion, and distortion of legitimate user are given. The inner bounds are derived by using uncoded scheme and (operationally) separate scheme, respectively. Thanks to the equivalence between lossy-equivocation secrecy and list secrecy, information spectrum method is leveraged to prove the outer bound. As special cases, the admissible region for the case of degraded wiretap channel or lossless communication for legitimate user has been characterized completely. For both these two cases, separate scheme is proven to be optimal. Interestingly, however, separation indeed suffers performance loss for other certain cases. Besides, we also extend our results to characterize the achievable region for Gaussian communication case. As a side product optimistic lossy source coding has also been addressed.

cs.IT↗

arXiv2016

Distortion Bounds for Transmitting Correlated Sources with Common Part over MAC

This paper investigates the joint source-channel coding problem of sending two correlated memoryless sources with common part over a memoryless multiple access channel (MAC). An inner bound and two outer bounds on the achievable distortion region are derived. In particular, they respectively recover the existing bounds for several special cases, such as communication without common part, lossless communication, and noiseless communication. When specialized to quadratic Gaussian communication case, transmitting Gaussian sources with Gaussian common part over Gaussian MAC, the inner bound and outer bound are used to generate two new bounds. Numerical result shows that common part improves the distortion of such distributed source-channel coding problem.

cs.IT↗

arXiv2016

Online Segment to Segment Neural Transduction

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits exact polynomial marginalization of the latent segmentation during training, and during decoding beam search is employed to find the best alignment path together with the predicted output sequence. Our model tackles the bottleneck of vanilla encoder-decoders that have to read and memorize the entire input sequence in their fixed-length hidden states before producing any output. It is different from previous attentive models in that, instead of treating the attention weights as output of a deterministic function, our model assigns attention weights to a sequential latent variable which can be marginalized out and permits online generation. Experiments on abstractive sentence summarization and morphological inflection show significant performance gains over the baseline encoder-decoders.

cs.CL↗

arXiv2016

Comments on "Approximate Characterizations for the Gaussian Source Broadcast Distortion Region"

Recently, Tian et al. [1] considered joint source-channel coding of transmitting a Gaussian source over $K$-user Gaussian broadcast channel, and derived an outer bound on the admissible distortion region. In [1], they stated "due to its nonlinear form, it appears difficult to determine whether it is always looser than the trivial outer bound in all distortion regimes with bandwidth compression". However, in this correspondence we solve this problem and prove that for the bandwidth expansion case ($K\geq2$), this outer bound is strictly tighter than the trivial outer bound with each user being optimal in the point-to-point setting; while for the bandwidth compression or bandwidth match case, this outer bound actually degenerates to the trivial outer bound. Therefore, our results imply that on one hand, the outer bound given in [1] is nontrivial only for Gaussian broadcast communication ($K\geq2$) with bandwidth expansion; on the other hand, unfortunately, no nontrivial outer bound exists so far for Gaussian broadcast communication ($K\geq2$) with bandwidth compression.

cs.IT↗

arXiv2016

Line Spectral Estimation Based on Compressed Sensing with Deterministic Sub-Nyquist Sampling

As an alternative to the traditional sampling theory, compressed sensing allows acquiring much smaller amount of data, still estimating the spectra of frequency-sparse signals accurately. However, compressed sensing usually requires random sampling in data acquisition, which is difficult to implement in hardware. In this paper, we propose a deterministic and simple sampling scheme, that is, sampling at three sub-Nyquist rates which have coprime undersampled ratios. This sampling method turns out to be valid through numerical experiments. A complex-valued multitask algorithm based on variational Bayesian inference is proposed to estimate the spectra of frequency-sparse signals after sampling. Simulations show that this method is feasible and robust at quite low sampling rates.

cs.IT↗

arXiv2016

Local exact boundary controllability of entropy solutions to a class of hyperbolic systems of conservation laws

In this paper, we study the local exact boundary controllability of entropy solutions to a class linearly degenerate hyperbolic systems of conservation laws with constant multiplicity. The authors prove the two-sided boundary controllability, one-sided boundary controllability and two-sided controllability with less controls, by applying the strategy used originally for classical solutions with essential modifications. Our constructive method is based on the well-posedness of semi-global solutions constructed by the limit of $ \e $-approximate front tracking solutions to the mixed initial-boundary value problem with general nonlinear boundary conditions and some further properties on both $ \e $-approximate front tracking solutions and entropy solutions.

math.OC↗

arXiv2016

Neural Variational Inference for Text Processing

Recent advances in neural variational inference have spawned a renaissance in deep latent variable models. In this paper we introduce a generic variational inference framework for generative and conditional models of text. While traditional variational methods derive an analytic approximation for the intractable distributions over latent variables, here we construct an inference network conditioned on the discrete text input to provide the variational distribution. We validate this framework on two very different text modelling applications, generative document modelling and supervised question answering. Our neural variational document model combines a continuous stochastic document representation with a bag-of-words generative model and achieves the lowest reported perplexities on two standard test corpora. The neural answer selection model employs a stochastic representation layer within an attention mechanism to extract the semantics between a question and answer pair. On two question answering benchmarks this model exceeds all previous published benchmarks.

cs.CL↗

arXiv2016

GPU-FV: Realtime Fisher Vector and Its Applications in Video Monitoring

Fisher vector has been widely used in many multimedia retrieval and visual recognition applications with good performance. However, the computation complexity prevents its usage in real-time video monitoring. In this work, we proposed and implemented GPU-FV, a fast Fisher vector extraction method with the help of modern GPUs. The challenge of implementing Fisher vector on GPUs lies in the data dependency in feature extraction and expensive memory access in Fisher vector computing. To handle these challenges, we carefully designed GPU-FV in a way that utilizes the computing power of GPU as much as possible, and applied optimizations such as loop tiling to boost the performance. GPU-FV is about 12 times faster than the CPU version, and 50\% faster than a non-optimized GPU implementation. For standard video input (320*240), GPU-FV can process each frame within 34ms on a model GPU. Our experiments show that GPU-FV obtains a similar recognition accuracy as traditional FV on VOC 2007 and Caltech 256 image sets. We also applied GPU-FV for realtime video monitoring tasks and found that GPU-FV outperforms a number of previous works. Especially, when the number of training examples are small, GPU-FV outperforms the recent popular deep CNN features borrowed from ImageNet. The code can be downloaded from the following link https://bitbucket.org/mawenjing/gpu-fv.

cs.CV↗