Zobrazeno 1 - 10
of 1 693
pro vyhledávání: '"Motani A"'
We study the two-user broadcast channel with degraded message sets and derive second-order achievability rate regions. Specifically, the channel noises are not necessarily Gaussian and we use spherical codebooks for both users. The weak user with wor
Externí odkaz:
http://arxiv.org/abs/2410.17540
Autor:
Tan, John Chong Min, Saroj, Prince, Runwal, Bharat, Maheshwari, Hardik, Sheng, Brian Lim Yi, Cottrill, Richard, Chona, Alankrit, Kumar, Ambuj, Motani, Mehul
TaskGen is an open-sourced agentic framework which uses an Agent to solve an arbitrary task by breaking them down into subtasks. Each subtask is mapped to an Equipped Function or another Agent to execute. In order to reduce verbosity (and hence token
Externí odkaz:
http://arxiv.org/abs/2407.15734
Autor:
Tan, John Chong Min, Motani, Mehul
We attempt to solve the Abstraction and Reasoning Corpus (ARC) Challenge using Large Language Models (LLMs) as a system of multiple expert agents. Using the flexibility of LLMs to be prompted to do various novel tasks using zero-shot, few-shot, conte
Externí odkaz:
http://arxiv.org/abs/2310.05146
Autor:
Ghosh, Rohan, Motani, Mehul
Most entropy measures depend on the spread of the probability distribution over the sample space $\mathcal{X}$, and the maximum entropy achievable scales proportionately with the sample space cardinality $|\mathcal{X}|$. For a finite $|\mathcal{X}|$,
Externí odkaz:
http://arxiv.org/abs/2304.02223
Autor:
Tan, John Chong Min, Motani, Mehul
Model-based next state prediction and state value prediction are slow to converge. To address these challenges, we do the following: i) Instead of a neural network, we do model-based planning using a parallel memory retrieval system (which we term th
Externí odkaz:
http://arxiv.org/abs/2301.13758
Autor:
Zhou, Lin, Motani, Mehul
Publikováno v:
Foundations and Trends in Communications and Information Theory: Vol. 20: No. 3, pp 157-389 (2023)
In this monograph, we review recent advances in second-order asymptotics for lossy source coding, which provides approximations to the finite blocklength performance of optimal codes. The monograph is divided into three parts. In part I, we motivate
Externí odkaz:
http://arxiv.org/abs/2301.07871
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 overfitting in overparameterized networks. However, in network pruning, we fin
Externí odkaz:
http://arxiv.org/abs/2212.06145
Autor:
Liu, Shiyu, Motani, Mehul
Mutual Information (MI) based feature selection makes use of MI to evaluate each feature and eventually shortlists a relevant feature subset, in order to address issues associated with high-dimensional datasets. Despite the effectiveness of MI in fea
Externí odkaz:
http://arxiv.org/abs/2212.06143
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, high variance forecasts and the latter leads to low variance, high bi
Externí odkaz:
http://arxiv.org/abs/2212.06142
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 (i.e., accuracy preserving subnetworks) can not be found without appl
Externí odkaz:
http://arxiv.org/abs/2212.06144