73 citations · 351 across the 14 of their papers we have counts for
14 papers
SUS backprop: linear backpropagation algorithm for long inputs in transformers
Sergey Pankov, Georges Harik
It is straightforward to design an unbiased gradient estimator that stochastically cuts the backpropagation flow through any part of a computational graph. By cutting the parts tha…
Energy-conserving intermittent-contact motion in complex models
Sergey Pankov
Some mechanical systems, that are modeled to have inelastic collisions, nonetheless possess energy-conserving intermittent-contact solutions, known as collisionless solutions. Such…
Configuration Path Control
Sergey Pankov
Reinforcement learning methods often produce brittle policies -- policies that perform well during training, but generalize poorly beyond their direct training experience, thus bec…
Three-dimensional bipedal model with zero-energy-cost walking
Sergey Pankov
We study a three-dimensional articulated rigid-body biped model that possesses zero cost of transport walking gaits. Energy losses are avoided due to the complete elimination of th…
Reward-estimation variance elimination in sequential decision processes
Sergey Pankov
Policy gradient methods are very attractive in reinforcement learning due to their model-free nature and convergence guarantees. These methods, however, suffer from high variance i…
Learning image transformations without training examples
Sergey Pankov
The use of image transformations is essential for efficient modeling and learning of visual data. But the class of relevant transformations is large: affine transformations, projec…