Related papers: Learning from Streaming Video with Orthogonal Grad…
Neural networks are achieving state of the art and sometimes super-human performance on learning tasks across a variety of domains. Whenever these problems require learning in a continual or sequential manner, however, neural networks…
In real-world contexts, sometimes data are available in form of Natural Data Streams, i.e. data characterized by a streaming nature, unbalanced distribution, data drift over a long time frame and strong correlation of samples in short time…
We introduce a novel algorithm for gradient-based optimization of stochastic objective functions. The method may be seen as a variant of SGD with momentum equipped with an adaptive learning rate automatically adjusted by an 'energy'…
Instructional video generation is an emerging task that aims to synthesize coherent demonstrations of procedural activities from textual descriptions. Such capability has broad implications for content creation, education, and human-AI…
Recent studies have shown that many nonconvex machine learning problems satisfy a generalized-smooth condition that extends beyond traditional smooth nonconvex optimization. However, the existing algorithms are not fully adapted to such…
Despite an extensive body of literature on deep learning optimization, our current understanding of what makes an optimization algorithm effective is fragmented. In particular, we do not understand well whether enhanced optimization…
Over the last few years, 360{\deg} video traffic on the network has grown significantly. A key challenge of 360{\deg} video playback is ensuring a high quality of experience (QoE) with limited network bandwidth. Currently, most studies…
This work demonstrates that training autoregressive video diffusion models from a single video stream$\unicode{x2013}$resembling the experience of embodied agents$\unicode{x2013}$is not only possible, but can also be as effective as…
The performance of an optimizer on large-scale deep learning models depends critically on fine-tuning the learning rate, often requiring an extensive grid search over base learning rates, schedules, and other hyperparameters. In this paper,…
We propose a stochastic optimization method for minimizing loss functions, expressed as an expected value, that adaptively controls the batch size used in the computation of gradient approximations and the step size used to move along such…
We describe the results of a randomized controlled trial of video-streaming algorithms for bitrate selection and network prediction. Over the last eight months, we have streamed 14.2 years of video to 56,000 users across the Internet.…
Machine learning algorithms aim to find patterns from observations, which may include some noise, especially in robotics domain. To perform well even with such noise, we expect them to be able to detect outliers and discard them when…
Video anticipation is the task of predicting one/multiple future representation(s) given limited, partial observation. This is a challenging task due to the fact that given limited observation, the future representation can be highly…
Many modern learning tasks involve fitting nonlinear models to data which are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Due to this overparameterization, the training…
Video generation models often operate under the assumption of fixed frame rates, which leads to suboptimal performance when it comes to handling flexible frame rates (e.g., increasing the frame rate of the more dynamic portion of the video…
The standard way of training video models entails sampling at each iteration a single clip from a video and optimizing the clip prediction with respect to the video-level label. We argue that a single clip may not have enough temporal…
In continual learning, a learner has to keep learning from the data over its whole life time. A key issue is to decide what knowledge to keep and what knowledge to let go. In a neural network, this can be implemented by using a step-size…
Autoregressively trained transformers have brought a profound revolution to the world, especially with their in-context learning (ICL) ability to address downstream tasks. Recently, several studies suggest that transformers learn a…
Media streaming has been adopted for a variety of applications such as entertainment, visualization, and design. Unlike video/audio streaming where the content is usually consumed sequentially, 3D applications such as gaming require…
Automated machine learning techniques benefited from tremendous research progress in recently. These developments and the continuous-growing demand for machine learning experts led to the development of numerous AutoML tools. However, these…