Search Results for author:
Found 71 papers, 39 papers with code
Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning
Discovering efficient algorithms for solving complex problems has been an outstanding challenge in mathematics and computer science, requiring substantial human expertise over the years.
Context-Aware Toxicity Detection in Multiplayer Games: Integrating Domain-Adaptive Pretraining and Match Metadata
The detrimental effects of toxicity in competitive online video games are widely acknowledged, prompting publishers to monitor player chat conversations.
From Markov to Laplace: How Mamba In-Context Learns Markov Chains
To explain this, we theoretically characterize the representation capacity of Mamba and reveal the fundamental role of convolution in enabling it to represent the optimal Laplacian smoothing.
Regret-Optimized Portfolio Enhancement through Deep Reinforcement Learning and Future Looking Rewards
This paper introduces a novel agent-based approach for enhancing existing portfolio strategies using Proximal Policy Optimization (PPO).
Optimizing LLM Inference for Database Systems: Cost-Aware Scheduling for Concurrent Requests
LLMs are increasingly used inside database systems and in database applications for better complexity management and decision-making, where LLM inferences require significant GPU costs.
Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders
We investigated the possibility of using SAEs to learn interpretable features for a few-step text-to-image diffusion models, such as SDXL Turbo.
Beyond Autoregression: Fast LLMs via Self-Distillation Through Time
Moreover, we demonstrate the efficacy of our approach for diffusion language models with up to 860M parameters.
SIKeD: Self-guided Iterative Knowledge Distillation for mathematical reasoning
While LLMs can accurately solve reasoning tasks through a variety of strategies, even without fine-tuning, smaller models are not expressive enough to fit the LLMs distribution on all strategies when distilled and tend to prioritize one strategy over the others.
The Role of Deep Learning Regularizations on Actors in Offline RL
Deep learning regularization techniques, such as dropout, layer normalization, or weight decay, are widely adopted in the construction of modern artificial neural networks, often resulting in more robust training processes and improved generalization capabilities.
In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning
Our work empirically explores model-free policy learning loss functions and the impact of different architectural choices.
Investigating Low-Rank Training in Transformer Language Models: Efficiency and Scaling Analysis
State-of-the-art LLMs often rely on scale with high computational costs, which has sparked a research agenda to reduce parameter counts and costs without significantly impacting performance.
HiPPO-Prophecy: State-Space Models can Provably Learn Dynamical Systems in Context
Specifically, we find an explicit weight construction for continuous SSMs and provide an asymptotic error bound on the derivative approximation.
Self-Recognition in Language Models
Instead, our results suggest that given a set of alternatives, LMs seek to pick the "best" answer, regardless of its origin.
Building on Efficient Foundations: Effectively Training LLMs with Structured Feedforward Layers
State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive.
Aligning Large Language Models with Diverse Political Viewpoints
Models aligned with this data can generate more accurate political viewpoints from Swiss parties, compared to commercial models such as ChatGPT.
PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer
At the low level, we used a Q-learning based approach called the Q-Performer to accomplish these sub-goals.
Fleet of Agents: Coordinated Problem Solving with Large Language Models using Genetic Particle Filtering
Large language models (LLMs) have significantly evolved, moving from simple output generation to complex reasoning and from stand-alone usage to being embedded into broader frameworks.
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO
For off-policy deep value-based RL methods, this phenomenon has been correlated with a decrease in representation rank and the ability to fit random targets, termed capacity loss.
Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models
Recurrent neural networks (RNNs) have fast inference and scale efficiently on long sequences, but they are difficult to train and hard to scale.
Simple Hierarchical Planning with Diffusion
Diffusion-based generative methods have proven effective in modeling trajectories with offline datasets.
Reinforced Self-Training (ReST) for Language Modeling
Reinforcement learning from human feedback (RLHF) can improve the quality of large language model's (LLM) outputs by aligning them with human preferences.
AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning
StarCraft II is one of the most challenging simulated reinforcement learning environments; it is partially observable, stochastic, multi-agent, and mastering StarCraft II requires strategic planning over long time horizons with real-time low-level execution.
Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues
Deep neural networks based on linear RNNs interleaved with position-wise MLPs are gaining traction as competitive approaches for sequence modeling.
Resurrecting Recurrent Neural Networks for Long Sequences
Recurrent Neural Networks (RNNs) offer fast inference on long sequences but are hard to optimize and slow to train.
An Empirical Study of Implicit Regularization in Deep Offline RL
Also, we empirically identify three phases of learning that explain the impact of implicit regularization on the learning dynamics and found that bootstrapping alone is insufficient to explain the collapse of the effective rank.
Active Offline Policy Selection
We use multiple benchmarks, including real-world robotics, with a large number of candidate policies to show that the proposed approach improves upon state-of-the-art OPE estimates and pure online policy evaluation.
On Instrumental Variable Regression for Deep Offline Policy Evaluation
By applying different IV techniques to OPE, we are not only able to recover previously proposed OPE methods such as model-based techniques but also to obtain competitive new techniques.
Regularized Behavior Value Estimation
Due to bootstrapping, these errors get amplified during training and can lead to divergence, thereby crippling learning.
Addressing Extrapolation Error in Deep Offline Reinforcement Learning
These errors can be compounded by bootstrapping when the function approximator overestimates, leading the value function to *grow unbounded*, thereby crippling learning.
RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
Offline Learning from Demonstrations and Unlabeled Experience
Behavior cloning (BC) is often practical for robot learning because it allows a policy to be trained offline without rewards, by supervised learning on expert demonstrations.
Hyperparameter Selection for Offline Reinforcement Learning
Therefore, in this work, we focus on \textit{offline hyperparameter selection}, i. e. methods for choosing the best policy from a set of many policies trained using different hyperparameters, given only logged data.
Critic Regularized Regression
Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction.
Post-Workshop Report on Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver
Science meets Engineering in Deep Learning took place in Vancouver as part of the Workshop section of NeurIPS 2019.
RL Unplugged: A Suite of Benchmarks for Offline Reinforcement Learning
We hope that our suite of benchmarks will increase the reproducibility of experiments and make it possible to study challenging tasks with a limited computational budget, thus making RL research both more systematic and more accessible across the community.
Acme: A Research Framework for Distributed Reinforcement Learning
These implementations serve both as a validation of our design decisions as well as an important contribution to reproducibility in RL research.
Improving the Gating Mechanism of Recurrent Neural Networks
Gating mechanisms are widely used in neural network models, where they allow gradients to backpropagate more easily through depth or time.
Stabilizing Transformers for Reinforcement Learning
Harnessing the transformer's ability to process long time horizons of information could provide a similar performance boost in partially observable reinforcement learning (RL) domains, but the large-scale transformers used in NLP have yet to be successfully applied to the RL setting.
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
This paper introduces R2D3, an agent that makes efficient use of demonstrations to solve hard exploration problems in partially observable environments with highly variable initial conditions.
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL
Therefore, we also employ influence to train agents to use an explicit communication channel, and find that it leads to more effective communication and higher collective reward.
Social Influence as Intrinsic Motivation for Multi-Agent Deep Reinforcement Learning
We propose a unified mechanism for achieving coordination and communication in Multi-Agent Reinforcement Learning (MARL), through rewarding agents for having causal influence over other agents' actions.
Sample Efficient Adaptive Text-to-Speech
Instead, the aim is to produce a network that requires few data at deployment time to rapidly adapt to new speakers.
Relational inductive biases, deep learning, and graph networks
As a companion to this paper, we have released an open-source software library for building graph networks, with demonstrations of how to use them in practice.
Hyperbolic Attention Networks
We introduce hyperbolic attention networks to endow neural networks with enough capacity to match the complexity of data with hierarchical and power-law structure.
Plan, Attend, Generate: Planning for Sequence-to-Sequence Models
We investigate the integration of a planning mechanism into sequence-to-sequence models using attention.
Memory Augmented Neural Networks for Natural Language Processing
We will present a unified architecture for Memory Augmented Neural Networks (MANN) and discuss the ways in which one can address the external memory and hence read/write from it.
Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning
We investigate the integration of a planning mechanism into an encoder-decoder architecture with attention.
Plan, Attend, Generate: Character-level Neural Machine Translation with Planning in the Decoder
We investigate the integration of a planning mechanism into an encoder-decoder architecture with an explicit alignment for character-level machine translation.
Gated Orthogonal Recurrent Units: On Learning to Forget
We present a novel recurrent neural network (RNN) based model that combines the remembering ability of unitary RNNs with the ability of gated RNNs to effectively forget redundant/irrelevant information in its memory.
Ranked #7 on
Question Answering
on bAbi
(Accuracy (trained on 1k) metric)
Machine Comprehension by Text-to-Text Neural Question Generation
We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers.
A Robust Adaptive Stochastic Gradient Method for Deep Learning
The information about the element-wise curvature of the loss function is estimated from the local statistics of the stochastic first order gradients.
Memory Augmented Neural Networks with Wormhole Connections
We use discrete addressing for read/write operations which helps to substantially to reduce the vanishing gradient problem with very long sequences.
Mollifying Networks
The optimization of deep neural networks can be more challenging than traditional convex optimization problems due to the highly non-convex nature of the loss function, e. g. it can involve pathological landscapes such as saddle-surfaces that can be difficult to escape for algorithms based on simple gradient descent.
Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
We investigate the mechanisms and effects of learning to read and write into a memory through experiments on Facebook bAbI tasks using both a feedforward and GRUcontroller.
Ranked #5 on
Question Answering
on bAbi
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
Pointing the Unknown Words
At each time-step, the decision of which softmax layer to use choose adaptively made by an MLP which is conditioned on the context.~We motivate our work from a psychological evidence that humans naturally have a tendency to point towards objects in the context or the environment when the name of an object is not known.~We observe improvements on two tasks, neural machine translation on the Europarl English to French parallel corpora and text summarization on the Gigaword dataset using our proposed model.
Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus
Over the past decade, large-scale supervised learning corpora have enabled machine learning researchers to make substantial advances.
Noisy Activation Functions
Common nonlinear activation functions used in neural networks can cause training difficulties due to the saturation behavior of the activation function, which may hide dependencies that are not visible to vanilla-SGD (using first order gradients only).
Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyond
In this work, we model abstractive text summarization using Attentional Encoder-Decoder Recurrent Neural Networks, and show that they achieve state-of-the-art performance on two different corpora.
Ranked #10 on
Text Summarization
on DUC 2004 Task 1
Policy Distillation
Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specific) networks and extensive training are needed to achieve good performance.
On Using Monolingual Corpora in Neural Machine Translation
Recent work on end-to-end neural network-based architectures for machine translation has shown promising results for En-Fr and En-De translation.
EmoNets: Multimodal deep learning approaches for emotion recognition in video
The task of the emotion recognition in the wild (EmotiW) Challenge is to assign one of seven emotions to short video clips extracted from Hollywood style movies.
Gated Feedback Recurrent Neural Networks
In this work, we propose a novel recurrent neural network (RNN) architecture.
ADASECANT: Robust Adaptive Secant Method for Stochastic Gradient
The convergence of SGD depends on the careful choice of learning rate and the amount of the noise in stochastic estimates of the gradients.
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
In this paper we compare different types of recurrent units in recurrent neural networks (RNNs).
Ranked #10 on
Music Modeling
on JSB Chorales
Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
Gradient descent or quasi-Newton methods are almost ubiquitously used to perform such minimizations, and it is often thought that a main source of difficulty for these local methods to find the global minimum is the proliferation of local minima with much higher error than the global minimum.
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN).
Ranked #48 on
Machine Translation
on WMT2014 English-French
How to Construct Deep Recurrent Neural Networks
Based on this observation, we propose two novel architectures of a deep RNN which are orthogonal to an earlier attempt of stacking multiple recurrent layers to build a deep RNN (Schmidhuber, 1992; El Hihi and Bengio, 1996).
Learned-Norm Pooling for Deep Feedforward and Recurrent Neural Networks
In this paper we propose and investigate a novel nonlinear unit, called $L_p$ unit, for deep neural networks.
