Search Results for author:
Found 23 papers, 6 papers with code
Near-optimal Per-Action Regret Bounds for Sleeping Bandits
In a setting with $K$ total arms and at most $A$ available arms in each round over $T$ rounds, the best known upper bound is $O(K\sqrt{TA\ln{K}})$, obtained indirectly via minimizing internal sleeping regrets.
VinaLLaMA: LLaMA-based Vietnamese Foundation Model
In this technical report, we present VinaLLaMA, an open-weight, state-of-the-art (SOTA) Large Language Model for the Vietnamese language, built upon LLaMA-2 with an additional 800 billion trained tokens.
Generalized Animal Imitator: Agile Locomotion with Versatile Motion Prior
This paper introduces the Versatile Instructable Motion prior (VIM) - a Reinforcement Learning framework designed to incorporate a range of agile locomotion tasks suitable for advanced robotic applications.
Segmenting mechanically heterogeneous domains via unsupervised learning
These highly deformable materials can have heterogeneous material properties, and can experience heterogeneous deformations with or without underlying material heterogeneity.
Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity
We also find that stacked ensembling provides no additional benefits to overall performance or fairness compared to either a local model or the zero-shot transfer procedure we tested.
Adversarial Online Multi-Task Reinforcement Learning
We prove a minimax lower bound of $\Omega(K\sqrt{DSAH})$ on the regret of any learning algorithm and an instance-specific lower bound of $\Omega(\frac{K}{\lambda^2})$ in sample complexity for a class of uniformly-good cluster-then-learn algorithms.
Challenges and perspectives in computational deconvolution of genomics data
Deciphering cell type heterogeneity is crucial for systematically understanding tissue homeostasis and its dysregulation in diseases.
FedDCT: Federated Learning of Large Convolutional Neural Networks on Resource Constrained Devices using Divide and Collaborative Training
FedDCT reduces the memory requirements and allows low-end devices to participate in FL.
Local Bayesian optimization via maximizing probability of descent
Local optimization presents a promising approach to expensive, high-dimensional black-box optimization by sidestepping the need to globally explore the search space.
Nonmyopic Multiclass Active Search with Diminishing Returns for Diverse Discovery
Active search is a setting in adaptive experimental design where we aim to uncover members of rare, valuable class(es) subject to a budget constraint.
Nonmyopic Multifidelity Active Search
Active search is a learning paradigm where we seek to identify as many members of a rare, valuable class as possible given a labeling budget.
Control and Simulation of a Grid-Forming Inverter for Hybrid PV-Battery Plants in Power System Black Start
This paper proposes the modeling, control, and simulation of a grid-forming inverter-based PV-battery power plant that can be used as a black start unit.
Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learning
Policies can be learned in only a few million time steps, even for challenging tasks of running over rough terrain with loads of over 100% of the nominal quadruped mass.
Robust Quadruped Jumping via Deep Reinforcement Learning
In this paper, we consider a general task of jumping varying distances and heights for a quadrupedal robot in noisy environments, such as off of uneven terrain and with variable robot dynamics parameters.
Robust Safety-Critical Control for Dynamic Robotics
We present a novel method of optimal robust control through quadratic programs that offers tracking stability while subject to input and state-based constraints as well as safety-critical constraints for nonlinear dynamical robotic systems in the presence of model uncertainty.
OV: Validity-based Optimistic Smart Contracts
Reasoning about the validity of the object states is challenging in concurrent smart contracts.
Distributed, Parallel, and Cluster Computing Programming Languages
Fast Stochastic Peer Selection in Proof-of-Stake Protocols
The problem of peer selection, which randomly selects a peer from a set, is commonplace in Proof-of-Stake (PoS) protocols.
Distributed, Parallel, and Cluster Computing Data Structures and Algorithms
StairDag: Cross-DAG Validation For Scalable BFT Consensus
Unlike StakeDag's DAG, x-DAG ensures that each new block has to have parent blocks from both Users and Validators to achieve more safety and liveness.
Cryptography and Security Distributed, Parallel, and Cluster Computing
StakeDag: Stake-based Consensus For Scalable Trustless Systems
We address a general model of trustless system in which participants are distinguished by their stake or trust: users and validators.
Distributed, Parallel, and Cluster Computing Cryptography and Security
ONLAY: Online Layering for scalable asynchronous BFT system
This paper presents a new framework, namely \emph{\onlay}, for scalable asynchronous distributed systems.
Distributed, Parallel, and Cluster Computing
Fantom: A scalable framework for asynchronous distributed systems
We describe \emph{Fantom}, a framework for asynchronous distributed systems.
Distributed, Parallel, and Cluster Computing
OPERA: Reasoning about continuous common knowledge in asynchronous distributed systems
Each event block is signed by the hashes of the creating node and its $k$ peers.
Distributed, Parallel, and Cluster Computing
The Dialog State Tracking Challenge with Bayesian Approach
Generative model has been one of the most common approaches for solving the Dialog State Tracking Problem with the capabilities to model the dialog hypotheses in an explicit manner.
