TECHNIQUES FOR ADAPTIVE QUANTIZATION LEVEL SELECTION IN FEDERATED LEARNING

    公开(公告)号:US20220245527A1

    公开(公告)日:2022-08-04

    申请号:US17164685

    申请日:2021-02-01

    Abstract: Methods, systems, and devices for wireless communications are described. To support adaptive quantization level selection in federated learning, a server may cause a base station to transmit an indication of a quantization level for a user equipment (UE) to use to compress gradient data output by a machine learning model. For example, the server may determine, for each UE of a set of UEs, a respective quantization level for respective gradient data that is output by a respective machine learning model at each UE. The server may transmit, to each UE via one or more base stations, first information for use as an input in the respective machine learning model and an indication of the respective quantization level. A UE may receive the first information and the indication and may transmit, to the server, compressed gradient data that is generated based on (e.g., using) the indicated quantization level.

    PRECODING TECHNIQUES FOR WIRELESS COMMUNICATIONS

    公开(公告)号:US20210359731A1

    公开(公告)日:2021-11-18

    申请号:US17246374

    申请日:2021-04-30

    Abstract: Methods, systems, and devices for wireless communications are described in which a base station may identify a null space matrix that lies within a null space of an effective channel matrix for communications between the base station and a user equipment (UE). An indication of the null space matrix may be provided to the UE, and the null space matrix used to determine modifications to a precoding matrix. The base station and UE may determine a redistribution matrix that provides a reduced variance of transmission powers for a number of transmission channels, where a product of the null space matrix and the redistribution matrix may be computed and added to the precoding matrix to generate a modified precoding matrix. The modified precoding matrix may be used to generate the communications from the base station and UE with reduced power variance across channels.

    COMPRESSED MEASUREMENT FEEDBACK USING AN ENCODER NEURAL NETWORK

    公开(公告)号:US20210266787A1

    公开(公告)日:2021-08-26

    申请号:US17180124

    申请日:2021-02-19

    Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may perform a measurement operation to attain multiple measurements to report to a base station. The measurements may correspond to a first number of bits if reported. The UE may compress the measurements using an encoder neural network (NN) to obtain an encoder output indicating the measurements. This encoder output may include a second number of bits that is less than the first number of bits. The UE may report the encoder output to the base station in this compressed form. At the base station, the encoder output may be decompressed according to a decoder NN. Once the base station decompresses the encoder output, the UE and base station may communicate according to the measurements determined from the decompression. In some cases, the base station may perform load redistribution based on the measurements.

    COOPERATIVE EVENT WARNING SYSTEM
    507.
    发明申请

    公开(公告)号:US20210243556A1

    公开(公告)日:2021-08-05

    申请号:US17160267

    申请日:2021-01-27

    Abstract: Methods, systems, and devices for wireless communications are described. A first wireless device may receive situational information for a second wireless device over a first communication link between the first wireless device and the second wireless device and situational information for a third wireless device over a second communication link between the first wireless device and the third wireless device. The first wireless device may transmit message with guidance information to the second wireless device on behalf of the third wireless device and based on the second wireless device and the third wireless device having an event likelihood above a threshold. The event likelihood may be based on the situational information for the second wireless device and the situational information for the third wireless device.

    NEURAL NETWORK AND ANTENNA CONFIGURATION INDICATION

    公开(公告)号:US20210194548A1

    公开(公告)日:2021-06-24

    申请号:US17247664

    申请日:2020-12-18

    Abstract: Wireless communications systems and methods related to indicating antenna configuration information and neural network information are disclosed. Neural network information may be selected for an encoder side based on an antenna configuration of a first device housing the encoder. This information may be transmitted with the antenna configuration information to a second device, which may jointly train the neural network with the first device. The first device may further transmit one or more weights after the training, which are stored with the antenna configuration information at the second device as well. When a third device with similar antenna configuration as the first device establishes communication with the second device, the second device may transmit neural network information, as well as weights, to the third device. The third device may use this information, instead of default information, to speed up neural network initialization and training.

    Quasi-colocation for LBT
    509.
    发明授权

    公开(公告)号:US10986665B2

    公开(公告)日:2021-04-20

    申请号:US16046500

    申请日:2018-07-26

    Abstract: Quasi-colocation (QCL) for listen before talk (LBT) procedures is disclosed. A base station having a plurality of antennas may identify one or more groups of QCL antennas. Various aspects provide for different rules defining the QCL relationship, such as base on interference experienced by the antennas, a physical or logical connection of the antennas and LBT coupling, or synchronization. QCL may further be determined across multiple shared channels, such as based on frequency separation or frequency band of the channels. Once grouped as QCL, the base station performs the LBT procedure to reserve access to the one or more shared communication channels. If the LBT is successful, the base station may then transmit a channel reservation preamble on the shared communication channels in response.

Patent Agency Ranking