Abstract: A method includes accessing a plurality of weight matrices of a machine learning model. The method also includes, for each weight matrix, decomposing the weight matrix into a U matrix, an S matrix, and a V matrix using singular value decomposition. The S matrix is a diagonal matrix, and a singular group corresponds to each element in the S matrix. The method further includes, for each weight matrix, determining an importance score of each singular group. The importance score of the singular group represents a change in loss if the singular group is removed from the machine learning model. The method also includes, for each weight matrix, ranking the singular groups across the plurality of weight matrices based on the importance scores. In addition, the method includes, for each weight matrix, identifying one or more of the singular groups to prune based on the ranking of the singular groups.

Abstract: In one embodiment, a method includes accessing at least a portion of a training dataset for a trained neural network that includes multiple layers, where each layer includes a number of parameters, and where the training dataset includes multiple training samples that each include an input and a ground-truth output used to train the trained neural network. The method further includes training a hypernetwork to generate a layer-specific compression mask for each of one or more of the multiple layers of the trained neural network. The method further includes generating, by the trained hypernetwork, a final layer-specific compression mask for the trained neural network and compressing the trained neural network by reducing, for each of the one or more layers of the neural network, the number of parameters of that layer according to the final layer-specific compression mask.

Abstract: A dispenser for sheet materials includes a top portion, a bottom portion, and a restraining member preventing the top and bottom portion from separating. The top portion and the bottom portion can telescope to vary the dispenser's overall height. In one embodiment, by designing a dispenser having bottom sidewalls and top sidewalls of approximately the same length, problems with access to the exposed sheet or excessive manipulation to change the dispenser's height can be avoided. In another embodiment, by designing the dispenser such that the height of the dispenser can automatically reduce as the sheet material is depleted or where the height can be adjusted by simply pushing down on the dispenser's top makes the dispenser convenient to use.

Abstract: A paper web having discrete elevated elements molded in the z-direction is generally disclosed, along with methods of making the same. The molded web has improved bulk retention when subjected to compression in the z-direction. The discrete elevated elements can be dome-shaped elevated elements and/or elevated elements having at least one vertical sidewall to form an aesthetically pleasing figure. The paper web can be an uncreped through air dried paper web. The molding of the paper web can result from the contour of the dryer fabric, such as a nonwoven dryer fabric.

Abstract: A dispenser for sheet materials includes a top portion, a bottom portion, and a restraining member preventing the top and bottom portion from separating. The top portion and the bottom portion can telescope to vary the dispenser's overall height. In one embodiment, by designing a dispenser having bottom sidewalls and top sidewalls of approximately the same length, problems with access to the exposed sheet or excessive manipulation to change the dispenser's height can be avoided. In another embodiment, by designing the dispenser such that the height of the dispenser can automatically reduce as the sheet material is depleted or where the height can be adjusted by simply pushing down on the dispenser's top makes the dispenser convenient to use.