Related papers: Streaming Linear System Identification with Revers…

This work investigates the problem of estimating the weight matrices of a stable time-invariant linear dynamical system from a single sequence of noisy measurements. We show that if the unknown weight matrices describing the system are in…

Neural enhancement through super-resolution (SR) deep neural networks (DNNs) opens up new possibilities for ultra-high-definition (UHD) live streaming over existing encoding and networking infrastructure. Yet, the heavy SR DNN inference…

The standard way to estimate the parameters $\Theta_\text{SEIR}$ (e.g., the transmission rate $\beta$) of an SEIR model is to use grid search, where simulations are performed on each set of parameters, and the parameter set leading to the…

Distillation-based acceleration has become foundational for making autoregressive streaming video diffusion models practical, with distribution matching distillation (DMD) as the de facto choice. Existing methods, however, train the student…

Experience replay enables data-efficient learning from past experiences in online reinforcement learning agents. Traditionally, experiences were sampled uniformly from a replay buffer, regardless of differences in experience-specific…

In the adversarially robust streaming model, a stream of elements is presented to an algorithm and is allowed to depend on the output of the algorithm at earlier times during the stream. In the classic insertion-only model of data streams,…

The stochastic gradient descent (SGD) algorithm is the algorithm we use to train neural networks. However, it remains poorly understood how the SGD navigates the highly nonlinear and degenerate loss landscape of a neural network. In this…

In the context of a short video & live stream mixed recommendation scenario, the live stream recommendation system (RS) decides whether to allocate at most one live stream into the video feed for each user request. To maximize long-term…

We propose SLARM, a feed-forward model that unifies dynamic scene reconstruction, semantic understanding, and real-time streaming inference. SLARM captures complex, non-uniform motion through higher-order motion modeling, trained solely on…

This paper studies a risk minimization problem with decision dependent data distribution. The problem pertains to the performative prediction setting in which a trained model can affect the outcome estimated by the model. Such dependency…

There is a growing interest in the speech community in developing Recurrent Neural Network Transducer (RNN-T) models for automatic speech recognition (ASR) applications. RNN-T is trained with a loss function that does not enforce temporal…

Diffusion approximation provides weak approximation for stochastic gradient descent algorithms in a finite time horizon. In this paper, we introduce new tools motivated by the backward error analysis of numerical stochastic differential…

This paper introduces an online approach for identifying time-varying subspaces defined by linear dynamical systems. The approach of representing linear systems by non-parametric subspace models has received significant interest in the…

We introduce a streaming framework for analyzing stochastic approximation/optimization problems. This streaming framework is analogous to solving optimization problems using time-varying mini-batches that arrive sequentially. We provide…

We study offline off-dynamics reinforcement learning (RL) to utilize data from an easily accessible source domain to enhance policy learning in a target domain with limited data. Our approach centers on return-conditioned supervised…

Synthetic data generation (SDG) is a promising approach for enabling data sharing in biomedical studies while preserving patient privacy. Yet, state-of-the-art generative models often require large datasets and complex training procedures,…

In this paper we consider estimating the system parameters and designing stable observer for unknown noisy linear time-invariant (LTI) systems. We propose a Support Vector Regression (SVR) based estimator to provide adjustable asymmetric…

Stochastic gradient descent (SGD) is a widely adopted iterative method for optimizing differentiable objective functions. In this paper, we propose and discuss a novel approach to scale up SGD in applications involving non-convex functions…

Control systems are inevitably affected by external disturbances, and a major objective of the control design is to attenuate or eliminate their adverse effects on the system performance. This paper presents a disturbance rejection approach…

Streaming adaptations of manifold learning based dimensionality reduction methods, such as Isomap, are based on the assumption that a small initial batch of observations is enough for exact learning of the manifold, while remaining…