Search Results for author:
Found 40 papers, 10 papers with code
Online Preference Alignment for Language Models via Count-based Exploration
Then, we reformulate our objective to direct preference optimization with an exploration term, where the UCB-term can be converted to a count-based exploration bonus.
Integrating Language-Image Prior into EEG Decoding for Cross-Task Zero-Calibration RSVP-BCI
Specifically, we propose a prompt encoder based on the language-image pre-trained model to extract language-image features from task-specific prompts and stimulus images as prior knowledge for enhancing EEG decoding.
Forward KL Regularized Preference Optimization for Aligning Diffusion Policies
In this work, we propose a novel framework, Forward KL regularized Preference optimization for aligning Diffusion policies, to align the diffusion policy with preferences directly.
Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning
This paper investigates multi-objective reinforcement learning (MORL), which focuses on learning Pareto optimal policies in the presence of multiple reward functions.
Multi-Objective Reinforcement Learning
reinforcement-learning
+1
Pessimism Meets Risk: Risk-Sensitive Offline Reinforcement Learning
We study risk-sensitive reinforcement learning (RL), a crucial field due to its ability to enhance decision-making in scenarios where it is essential to manage uncertainty and minimize potential adverse outcomes.
Human-like object concept representations emerge naturally in multimodal large language models
The conceptualization and categorization of natural objects in the human mind have long intrigued cognitive scientists and neuroscientists, offering crucial insights into human perception and cognition.
ROPO: Robust Preference Optimization for Large Language Models
Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses.
Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
Additionally, DPA models user preferences as directions (i. e., unit vectors) in the reward space to achieve user-dependent preference control.
Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems.
A Temporal-Spectral Fusion Transformer with Subject-Specific Adapter for Enhancing RSVP-BCI Decoding
The performance improvement of traditional decoding methods relies on a substantial amount of training data from new test subjects, which increases preparation time for BCI systems.
StairNetV3: Depth-aware Stair Modeling using Deep Learning
Experiments on our dataset show that our method has a significant improvement over the previous best monocular vision method, with an intersection over union (IOU) increase of 3. 4 %, and the lightweight version has a fast detection speed and can meet the requirements of most real-time applications.
On the Value of Myopic Behavior in Policy Reuse
Leveraging learned strategies in unfamiliar scenarios is fundamental to human intelligence.
RGB-D-based Stair Detection using Deep Learning for Autonomous Stair Climbing
Specifically, we design a selective module, which can make the network learn the complementary relationship between the RGB map and the depth map and effectively combine the information from the RGB map and the depth map in different scenes.
Contrastive UCB: Provably Efficient Contrastive Self-Supervised Learning in Online Reinforcement Learning
Moreover, under the online setting, we propose novel upper confidence bound (UCB)-type algorithms that incorporate such a contrastive loss with online RL algorithms for MDPs or MGs.
Provably Efficient Fictitious Play Policy Optimization for Zero-Sum Markov Games with Structured Transitions
Our algorithms feature a combination of Upper Confidence Bound (UCB)-type optimism and fictitious play under the scope of simultaneous policy optimization in a non-stationary environment.
Stochastic Gradient Descent without Full Data Shuffle
In this paper, we first conduct a systematic empirical study on existing data shuffling strategies, which reveals that all existing strategies have room for improvement -- they all suffer in terms of I/O performance or convergence rate.
Learning Dynamic Mechanisms in Unknown Environments: A Reinforcement Learning Approach
Dynamic mechanism design studies how mechanism designers should allocate resources among agents in a time-varying environment.
Deep Leaning-Based Ultra-Fast Stair Detection
Staircases are some of the most common building structures in urban environments.
Safe Screening for Sparse Conditional Random Fields
To the best of our knowledge, this is the first screening method which introduces the dual optimum estimation technique -- by carefully exploring and exploiting the strong convexity and the complex structure of the dual problem -- in static screening methods to dynamic screening.
On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game
Then, given any extrinsic reward, the agent computes the policy via a planning algorithm with offline data collected in the exploration phase.
VisDrone-CC2020: The Vision Meets Drone Crowd Counting Challenge Results
Crowd counting on the drone platform is an interesting topic in computer vision, which brings new challenges such as small object inference, background clutter and wide viewpoint.
Stylized Neural Painting
Different from previous image-to-image translation methods that formulate the translation as pixel-wise prediction, we deal with such an artistic creation process in a vectorized environment and produce a sequence of physically meaningful stroke parameters that can be further used for rendering.
Single-Timescale Stochastic Nonconvex-Concave Optimization for Smooth Nonlinear TD Learning
Existing approaches for this problem are based on two-timescale or double-loop stochastic gradient algorithms, which may also require sampling large-batch data.
Low-Resource Generation of Multi-hop Reasoning Questions
Specifically, we first build a multi-hop generation model and guide it to satisfy the logical rationality by the reasoning chain extracted from a given text.
Gradient-Variation Bound for Online Convex Optimization with Constraints
We study online convex optimization with constraints consisting of multiple functional constraints and a relatively simple constraint set, such as a Euclidean ball.
Energy-Aware DNN Graph Optimization
Unlike existing work in deep neural network (DNN) graphs optimization for inference performance, we explore DNN graph optimization for energy awareness and savings for power- and resource-constrained machine learning devices.
Referring Image Segmentation by Generative Adversarial Learning
To this end, we propose to train the referring image segmentation model in a generative adversarial fashion, which well addresses the distribution similarity problem.
Upper Confidence Primal-Dual Reinforcement Learning for CMDP with Adversarial Loss
In particular, we prove that the proposed algorithm achieves $\widetilde{\mathcal{O}}(L|\mathcal{S}|\sqrt{|\mathcal{A}|T})$ upper bounds of both the regret and the constraint violation, where $L$ is the length of each episode.
Central Server Free Federated Learning over Single-sided Trust Social Networks
However, in many social network scenarios, centralized federated learning is not applicable (e. g., a central agent or server connecting all users may not exist, or the communication cost to the central server is not affordable).
PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
The key problem in graph node embedding lies in how to define the dependence to neighbors.
Robust One-Bit Recovery via ReLU Generative Networks: Improved Statistical Rate and Global Landscape Analysis
In this paper, we consider a new framework for the one-bit sensing problem where the sparsity is implicitly enforced via mapping a low dimensional representation $x_0$ through a known $n$-layer ReLU generative network $G:\mathbb{R}^k\rightarrow\mathbb{R}^d$.
Robust One-Bit Recovery via ReLU Generative Networks: Near-Optimal Statistical Rate and Global Landscape Analysis
Specifically, we consider a new framework for this problem where the sparsity is implicitly enforced via mapping a low dimensional representation $x_0 \in \mathbb{R}^k$ through a known $n$-layer ReLU generative network $G:\mathbb{R}^k\rightarrow\mathbb{R}^d$ such that $\theta_0 = G(x_0)$.
$\texttt{DeepSqueeze}$: Decentralization Meets Error-Compensated Compression
Since the \emph{decentralized} training has been witnessed to be superior to the traditional \emph{centralized} training in the communication restricted scenario, therefore a natural question to ask is "how to apply the error-compensated technology to the decentralized learning to further reduce the communication cost."
Which Factorization Machine Modeling is Better: A Theoretical Answer with Optimal Guarantee
This bound is sub-optimal comparing to the information theoretical lower bound $\mathcal{O}(kd)$.
Decentralized Online Learning: Take Benefits from Others' Data without Sharing Your Own to Track Global Trend
Decentralized Online Learning (online learning in decentralized networks) attracts more and more attention, since it is believed that Decentralized Online Learning can help the data providers cooperatively better solve their online problems without sharing their private data to a third party or other providers.
Proximal Online Gradient is Optimum for Dynamic Regret
While the online gradient method has been shown to be optimal for the static regret metric, the optimal algorithm for the dynamic regret remains unknown.
P^2IR: Universal Deep Node Representation via Partial Permutation Invariant Set Functions
Our method can 1) learn an arbitrary form of the representation function from the neighborhood, without losing any potential dependence structures, 2) automatically decide the significance of neighbors at different distances, and 3) be applicable to both homogeneous and heterogeneous graph embedding, which may contain multiple types of nodes.
GESF: A Universal Discriminative Mapping Mechanism for Graph Representation Learning
Graph embedding is a central problem in social network analysis and many other applications, aiming to learn the vector representation for each node.
Nonconvex One-bit Single-label Multi-label Learning
We study an extreme scenario in multi-label learning where each training instance is endowed with a single one-bit label out of multiple labels.
The Second Order Linear Model
We show that the conventional gradient descent heuristic is biased by the skewness of the distribution therefore is no longer the best practice of learning the SLM.
