35 citations · 70 across the 10 of their papers we have counts for
11 papers
Tab-PET: Graph-Based Positional Encodings for Tabular Transformers
Yunze Leng, Rohan Ghosh, Mehul Motani
Supervised learning with tabular data presents unique challenges, including low data sizes, the absence of structural cues, and heterogeneous features spanning both categorical and…
Local Intrinsic Dimensional Entropy
Rohan Ghosh, Mehul Motani
Most entropy measures depend on the spread of the probability distribution over the sample space , and the maximum entropy achievable scales proportionately with the s…
Optimizing Learning Rate Schedules for Iterative Pruning of Deep Neural Networks
Shiyu Liu, Rohan Ghosh, John Tan Chong Min +1
The importance of learning rate (LR) schedules on network pruning has been observed in a few recent works. As an example, Frankle and Carbin (2019) highlighted that winning tickets…
AP: Selective Activation for De-sparsifying Pruned Neural Networks
Shiyu Liu, Rohan Ghosh, Dylan Tan +1
The rectified linear unit (ReLU) is a highly successful activation function in neural networks as it allows networks to easily obtain sparse representations, which reduces overfitt…
Achieving Low Complexity Neural Decoders via Iterative Pruning
Vikrant Malik, Rohan Ghosh, Mehul Motani
The advancement of deep learning has led to the development of neural decoders for low latency communications. However, neural decoders can be very complex which can lead to increa…
Towards Better Long-range Time Series Forecasting using Generative Adversarial Networks
Shiyu Liu, Rohan Ghosh, Mehul Motani
Long-range time series forecasting is usually based on one of two existing forecasting strategies: Direct Forecasting and Iterative Forecasting, where the former provides low bias,…