Zobrazeno 1 - 10
of 7 316
pro vyhledávání: '"Rupam ."'
Autor:
Wei, Wei-Shao, Videbæk, Thomas E., Hayakawa, Daichi, Saha, Rupam, Rogers, W. Benjamin, Fraden, Seth
Self-assembly of nanoscale synthetic subunits is a promising bottom-up strategy for fabrication of functional materials. Here, we introduce a design principle for DNA origami nanoparticles of 50-nm size, exploiting modularity, to make a family of ver
Externí odkaz:
http://arxiv.org/abs/2411.09801
Autor:
Singh, Gurinder, Barman, Rupam
Let $t\geq2$ and $k\geq1$ be integers. A $t$-regular partition of a positive integer $n$ is a partition of $n$ such that none of its parts is divisible by $t$. A $t$-distinct partition of a positive integer $n$ is a partition of $n$ such that any of
Externí odkaz:
http://arxiv.org/abs/2410.15088
Natural intelligence processes experience as a continuous stream, sensing, acting, and learning moment-by-moment in real time. Streaming learning, the modus operandi of classic reinforcement learning (RL) algorithms like Q-learning and TD, mimics nat
Externí odkaz:
http://arxiv.org/abs/2410.14606
Autor:
Antony, Deepa, Barman, Rupam
Let $(x_n)_{n\geq0}$ be a linear recurrence sequence of order $k\geq2$ satisfying $$x_n=a_1x_{n-1}+a_2x_{n-2}+\dots+a_kx_{n-k}$$ for all integers $n\geq k$, where $a_1,\dots,a_k,x_0,\dots, x_{k-1}\in \mathbb{Z},$ with $a_k\neq0$. In 2017, Sanna posed
Externí odkaz:
http://arxiv.org/abs/2408.06949
Publikováno v:
Physics Letters B, Volume 857, October 2024, 138985
Event-by-event fluctuations in the initial stages of ultrarelativistic nucleus-nucleus collisions depend little on rapidity. The hydrodynamic expansion which occurs in later stages then gives rise to correlations among outgoing particles which depend
Externí odkaz:
http://arxiv.org/abs/2407.17313
Many failures in deep continual and reinforcement learning are associated with increasing magnitudes of the weights, making them hard to change and potentially causing overfitting. While many methods address these learning failures, they often change
Externí odkaz:
http://arxiv.org/abs/2407.01704
Autor:
Vasan, Gautham, Wang, Yan, Shahriar, Fahim, Bergstra, James, Jagersand, Martin, Mahmood, A. Rupam
Many real-world robot learning problems, such as pick-and-place or arriving at a destination, can be seen as a problem of reaching a goal state as soon as possible. These problems, when formulated as episodic reinforcement learning tasks, can easily
Externí odkaz:
http://arxiv.org/abs/2407.00324
Autor:
Ishfaq, Haque, Tan, Yixin, Yang, Yu, Lan, Qingfeng, Lu, Jianfeng, Mahmood, A. Rupam, Precup, Doina, Xu, Pan
Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to implement and not generalizable to Deep RL. While the emerging approxima
Externí odkaz:
http://arxiv.org/abs/2406.12241
Second-order information is valuable for many applications but challenging to compute. Several works focus on computing or approximating Hessian diagonals, but even this simplification introduces significant additional costs compared to computing a g
Externí odkaz:
http://arxiv.org/abs/2406.03276
Autor:
Che, Fengdi, Xiao, Chenjun, Mei, Jincheng, Dai, Bo, Gummadi, Ramki, Ramirez, Oscar A, Harris, Christopher K, Mahmood, A. Rupam, Schuurmans, Dale
Publikováno v:
Proceedings of the 41 st International Conference on Machine Learning, 2024
We prove that the combination of a target network and over-parameterized linear function approximation establishes a weaker convergence condition for bootstrapped value estimation in certain cases, even with off-policy data. Our condition is naturall
Externí odkaz:
http://arxiv.org/abs/2405.21043