Compression Group

We help to implement and optimize the resources of advanced deep learning models:

Pruning
We create methods for thinning the weights and relationships of models in order to optimize the resources consumed by the model.
Distillation
We are exploring ways to train light models at the output of heavy analogues without loss as a solution to the final problem.
Evaluation of the potential quality of the model
We create methods for predicting the expected quality of the model on specific samples to automate the selection of the best candidates.
Effective methods of training models
We apply algorithms for automated initialization, optimization, and change approaches to model training to accelerate convergence to the best model configuration.
Compression Group clients form model optimization goals such as reducing OPEX for training and applying neural network models
We have identified the most frequent optimization requests:
Optimization at the stage of model application
Our customers are interested in reducing the resources consumed by the model: RAM, CPU and GPU, SSD, power consumption. Reducing the necessary resources leads to an improvement in user characteristics: the speed of operation, the retention of charge by the device, etc.
Optimization of learning processes
Training of complex neural network architectures takes a lot of time and requires a large amount of computing resources. To save money, it is necessary to automate and optimize the processes of training and choosing the best models.
Preparing to transfer to the device
Saving on resources is also possible when transferring the computing load from a centralized to a decentralized format (that is, to user devices). In order for the device to have enough resources to start up, it is necessary to optimize the model.
Compatibility with new calculators
Analog chips are available on the market, where models can be integrated; low-bit processors that accelerate calculations in low-bit operations, and so on. It is possible to run only those models that fulfill the specified restrictions on them.
The library of compression methods developed on the basis of our experience allows us to reduce the risks of achieving results and accelerate the delivery of solutions to the customer
Quality
our methods are superior to the quality of ready-made Pwtorch or Tensorflow methods for complex architectures
Measurability
the results of our methods are provided by honest methods of comparing the resources consumed
Flexibility
in adapting the methods to the customer's tasks, the solution architecture and research approach are provided
Guarantees
the results from the compression team are confirmed by a successful project track
The research results are fully transmitted to the client
Software implementation
An easy-to-use library for with readable and reproducible code
Database of materials
A database of materials with reviews for a quick dive into the field and a technical report
Trained models
Parameters of trained models packed in the format required by the client
Anything else
We can prepare project artifacts in the format required by the customer
Compression Group optimized models for:
Scientific consultants of Compression Group
Konstantin Vorontsov
Prof MIPT
Specialisation: NLP
Vadim Strijov
Prof MIPT
Specialisation: Sensors
Mikhail Burtsev
Prof MIPT
Specialisation: NLP
Radoslav Neychev
Consult
Specialisation: Sensors
Andrey Leonidov
Prof MIPT
Specialisation: ML
Andrey Raygorodsky
Prof MIPT
Specialisation: ML, Graphs
Ilya Zharikov
Consult
Specialisation: DL & Sensors
Oleg Bakhteev
Consult
Specialisation: DL
Compression Group Project Results
Have a Project for us? 
Describe the problem you need to solve. We will contact you and clarify all the details!
Made on
Tilda