Search Results for author:
Found 30 papers, 7 papers with code
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
As a result, policy optimization is often trapped in a narrow region of the parameter space, leading to suboptimal alignment and performance.
Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo
Augmenting the multi-step reasoning abilities of Large Language Models (LLMs) has been a persistent challenge.
Apple Intelligence Foundation Language Models
We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute.
MindSet: Vision. A toolbox for testing DNNs on key psychological experiments
Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision.
Convolutional Neural Networks Trained to Identify Words Provide a Surprisingly Good Account of Visual Form Priming Effects
A wide variety of orthographic coding schemes and models of visual word identification have been developed to account for masked priming data that provide a measure of orthographic similarity between letter strings.
Sample Efficient Deep Reinforcement Learning via Local Planning
One useful property of simulators is that it is typically easy to reset the environment to a previously observed state.
Architecture Matters in Continual Learning
However, in this work, we show that the choice of architecture can significantly impact the continual learning performance, and different architectures lead to different trade-offs between the ability to remember previous tasks and learning new ones.
Wide Neural Networks Forget Less Catastrophically
A primary focus area in continual learning research is alleviating the "catastrophic forgetting" problem in neural networks by designing new algorithms that are more robust to the distribution shifts.
Morse-STF: Improved Protocols for Privacy-Preserving Machine Learning
Finally, we introduce Morse-STF, an end-to-end privacy-preserving system for machine learning training that leverages all these improved protocols.
Efficient Local Planning with Linear Function Approximation
Under the assumption that the Q-functions of all policies are linear in known features of the state-action pairs, we show that our algorithms have polynomial query and computational costs in the dimension of the features, the effective planning horizon, and the targeted sub-optimality, while these costs are independent of the size of the state space.
An Instance-Dependent Simulation Framework for Learning with Label Noise
We propose a simulation framework for generating instance-dependent noisy labels via a pseudo-labeling paradigm.
Revisiting the Loss Weight Adjustment in Object Detection
However, classification loss always dominates the multi-task loss in anchor-based methods, hampering the consistent and balanced optimization of the tasks.
Improved Regret Bound and Experience Replay in Regularized Policy Iteration
We first show that the regret analysis of the Politex algorithm (a version of regularized policy iteration) can be sharpened from $O(T^{3/4})$ to $O(\sqrt{T})$ under nearly identical assumptions, and instantiate the bound with linear function approximation.
The Effectiveness of Memory Replay in Large Scale Continual Learning
However, a degraded performance is observed for ER with small memory.
Optimization and Generalization of Regularization-Based Continual Learning: a Loss Approximation Viewpoint
This problem is often referred to as catastrophic forgetting, a key challenge in continual learning of neural networks.
A maximum-entropy approach to off-policy evaluation in average-reward MDPs
This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs).
An Efficient Framework for Clustered Federated Learning
We address the problem of federated learning (FL) where users are distributed and partitioned into clusters.
A Strong Feature Representation for Siamese Network Tracker
Firstly, the modified pre-trained VGG16 network is fine-tuned as the backbone.
Stochastic Gradient and Langevin Processes
We prove quantitative convergence rates at which discrete Langevin-like processes converge to the invariant distribution of a related stochastic differential equation.
A Fourier Perspective on Model Robustness in Computer Vision
Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision.
Robust Federated Learning in a Heterogeneous Environment
Then, leveraging the statistical model, we solve the robust heterogeneous Federated Learning problem \emph{optimally}; in particular our algorithm matches the lower bound on the estimation error in dimension and the number of data points.
Improving Robustness Without Sacrificing Accuracy with Patch Gaussian Augmentation
Deploying machine learning systems in the real world requires both high accuracy on clean data and robustness to naturally occurring corruptions.
Rademacher Complexity for Adversarially Robust Generalization
For binary linear classifiers, we prove tight bounds for the adversarial Rademacher complexity, and show that the adversarial Rademacher complexity is never smaller than its natural counterpart, and it has an unavoidable dimension dependence, unless the weight vector has bounded $\ell_1$ norm.
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning
In this setting, the Byzantine machines may create fake local minima near a saddle point that is far away from any true local minimum, even when robust gradient estimators are used.
A framework with updateable joint images re-ranking for Person Re-identification
In this paper, we propose a novel framework with rules of updating images for person re-identification in real-world surveillance system.
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
In particular, these algorithms are shown to achieve order-optimal statistical error rates for strongly convex losses.
Online Learning for Non-Stationary A/B Tests
The rollout of new versions of a feature in modern applications is a manual multi-stage process, as the feature is released to ever larger groups of users, while its performance is carefully monitored.
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
It has been experimentally observed that distributed implementations of mini-batch stochastic gradient descent (SGD) algorithms exhibit speedup saturation and decaying generalization ability beyond a particular batch-size.
Distributed Sequence Memory of Multidimensional Inputs in Recurrent Networks
In most existing analyses, the short-term memory (STM) capacity results conclude that the ESN network size must scale linearly with the input size for unstructured inputs.
Sliding-Window Optimization on an Ambiguity-Clearness Graph for Multi-object Tracking
Multi-object tracking remains challenging due to frequent occurrence of occlusions and outliers.
