25 citations · 64 across the 15 of their papers we have counts for
10 papers · 1 filter
QuZO: Quantized Zeroth-Order Fine-Tuning for Large Language Models
Jiajun Zhou, Yifan Yang, Kai Zhen +6
Language Models (LLMs) are often quantized to lower precision to reduce the memory cost and latency in inference. However, quantization often degrades model performance, thus fine-…
Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning
Ershad Banijamali, Mohsen Rohani, Elmira Amirloo +2
In autonomous driving (AD), accurately predicting changes in the environment can effectively improve safety and comfort. Due to complex interactions among traffic participants, how…
Deep Variational Sufficient Dimensionality Reduction
Ershad Banijamali, Amir-Hossein Karimi, Ali Ghodsi
We consider the problem of sufficient dimensionality reduction (SDR), where the high-dimensional observation is transformed to a low-dimensional sub-space in which the information…
Optimizing over a Restricted Policy Class in Markov Decision Processes
Ershad Banijamali, Yasin Abbasi-Yadkori, Mohammad Ghavamzadeh +1
We address the problem of finding an optimal policy in a Markov decision process under a restricted policy class defined by the convex hull of a set of base policies. This problem…
Disentangling Dynamics and Content for Control and Planning
Ershad Banijamali, Ahmad Khajenezhad, Ali Ghodsi +1
In this paper, We study the problem of learning a controllable representation for high-dimensional observations of dynamical systems. Specifically, we consider a situation where th…
JADE: Joint Autoencoders for Dis-Entanglement
Ershad Banijamali, Amir-Hossein Karimi, Alexander Wong +1
The problem of feature disentanglement has been explored in the literature, for the purpose of image and video processing and text analysis. State-of-the-art methods for disentangl…
Robust Locally-Linear Controllable Embedding
Ershad Banijamali, Rui Shu, Mohammad Ghavamzadeh +2
Embed-to-control (E2C) is a model for solving high-dimensional optimal control problems by combining variational auto-encoders with locally-optimal controllers. However, the E2C mo…
Fast Spectral Clustering Using Autoencoders and Landmarks
Ershad Banijamali, Ali Ghodsi
In this paper, we introduce an algorithm for performing spectral clustering efficiently. Spectral clustering is a powerful clustering algorithm that suffers from high computational…
Generative Mixture of Networks
Ershad Banijamali, Ali Ghodsi, Pascal Poupart
A generative model based on training deep architectures is proposed. The model consists of K networks that are trained together to learn the underlying distribution of a given data…
Semi-Supervised Representation Learning based on Probabilistic Labeling
Ershad Banijamali, Ali Ghodsi
In this paper, we present a new algorithm for semi-supervised representation learning. In this algorithm, we first find a vector representation for the labels of the data points ba…