Embodiments are generally directed to compression for compression for sparse data structures utilizing mode search approximation. An embodiment of an apparatus includes one or more processors including a graphics processor to process data; and a memory for storage of data, including compressed data. The one or more processors are to provide for compression of a data structure, including identification of a mode in the data structure, the data structure including a plurality of values and the mode being a most repeated value in a data structure, wherein identification of the mode includes application of a mode approximation operation, and encoding of an output vector to include the identified mode, a significance map to indicate locations at which the mode is present in the data structure, and remaining uncompressed data from the data structure.

Techniques are disclosed relating to compression of pixel data using different quantization for different regions of a block of pixels being compressed. In some embodiments, compression circuitry is configured to determine, for multiple components included in pixels of the block of pixels being compressed, respective smallest and greatest component values in respective regions of the block of pixels. The compression circuitry may determine, based on the determined smallest and greatest component values, to use a first number of bits to represent delta values relative to a base value for a first component in a first region and a second, different number of bits to represent delta values relative to a base value for a second component in the first region. The compression circuitry may then quantize delta values for the first and second components of pixels in the first region of the block of pixels using the determined first and second numbers of bits. In some embodiments, the compression circuitry determines whether to provide cross-component bit sharing within a region.

A method for partitioning of input vectors for coding is presented. The method comprises obtaining of an input vector. The input vector is segmented, in a non-recursive manner, into an integer number, N.sup.SEG, of input vector segments. A representation of a respective relative energy difference between parts of the input vector on each side of each boundary between the input vector segments is determined, in a recursive manner. The input vector segments and the representations of the relative energy differences are provided for individual coding. Partitioning units and computer programs for partitioning of input vectors for coding, as well as positional encoders, are presented.

An apparatus for encoding directional audio coding parameters comprising diffuseness parameters and direction parameters having a parameter calculator (100) for calculating the diffuseness parameters with a first time or frequency resolution and for calculating the direction parameters with a second time or frequency resolution; and a quantizer and encoder processor (200) for generating a quantized and encoded representation of the diffuseness parameters and the direction parameters.

Methods, apparatuses, and computer-readable medium for fronthaul compression are provided. An example method may include receiving, from a UE, uplink data via one or more active tones of a plurality of tones in a symbol, the uplink data corresponding to an access vector. The example method may further include compressing the uplink data based on a linear transformation of a pseudo-access vector generated based on the access vector, the linear transformation including a matrix, the compression enabling a second network entity to decompress the compressed uplink data without knowing one or more locations associated with the one or more active tones. The example method may further include transmitting, to the second network entity, the compressed uplink data.

Techniques are disclosed relating to detecting matching datasets using encode values. In various embodiments, a data monitoring system may perform encoding operations on a first dataset to generate a first encode value that corresponds to a particular one of one or more fields included in the first dataset. The data monitoring system may then determine whether the first dataset matches a previously analyzed dataset. For example, in some embodiments, data monitoring system may compare the first encode value to a previous encode value that corresponds to a second field of the previously analyzed dataset. Based on this comparison, the data monitoring system may generate an output value that is indicative of a similarity between the first encode value and the previous encode value. The data monitoring system may then determine whether the first dataset matches the previously analyzed dataset based on this output value.

A computer-implemented method for employing input-conditioned filters to perform natural language processing tasks using a convolutional neural network architecture includes receiving one or more inputs, generating one or more sets of filters conditioned on respective ones of the one or more inputs by implementing one or more encoders to encode the one or more inputs into one or more respective hidden vectors, and implementing one or more decoders to determine the one or more sets of filters based on the one or more hidden vectors, and performing adaptive convolution by applying the one or more sets of filters to respective ones of the one or more inputs to generate one or more representations.

It is inter alia disclosed an apparatus comprising: a table comprising a plurality of sub vectors, wherein each entry of the table is a subvector and each subvector have vector components which are the same as vector components of one or more basis code vectors; and a further table wherein an entry of the further table comprises a first pointer pointing to a sub vector in the table and a second pointer pointing to a subvector in the table, wherein the first pointer and the second pointer are arranged in the further table such that when vector components of the sub vector pointed to by the first pointer are combined with vector components of the sub vector pointed to by the second pointer a basis code vector is formed.

An apparatus for encoding directional audio coding parameters including diffuseness parameters and direction parameters includes: a parameter calculator for calculating the diffuseness parameters with a first time or frequency resolution and for calculating the direction parameters with a second time or frequency resolution; and a quantizer and encoder processor for generating a quantized and encoded representation of the diffuseness parameters and the direction parameters.

The present disclosure provides systems and methods for communication efficient distributed mean estimation. In particular, aspects of the present disclosure can be implemented by a system in which a number of vectors reside on a number of different clients, and a centralized server device seeks to estimate the mean of such vectors. According to one aspect of the present disclosure, a client computing device can rotate a vector by a random rotation matrix and then subsequently perform probabilistic quantization on the rotated vector. According to another aspect of the present disclosure, subsequent to quantization but prior to transmission, the client computing can encode the quantized vector according to a variable length coding scheme (e.g., by computing variable length codes).