Publications

The Software Documentor Mindset

Deeksha M. Arya

Jin L.C. Guo

Martin P. Robillard

Software technologies are used by programmers with diverse backgrounds. To fulfill programmers' need for information, enthusiasts contribute… (see more) numerous learning resources that vary in style and content, which act as documentation for the corresponding technology. We interviewed 26 volunteer documentation contributors, i.e. documentors, to understand why and how they create such documentation. From a qualitative analysis of our interviews, we identified a total of sixteen considerations that documentors have during the documentation contribution process, along three dimensions, namely motivations, topic selection techniques, and styling objectives. We grouped related considerations based on common underlying themes, to elicit five software documentor mindsets that occur during documentation contribution activities. We propose a structure of mindsets, and their associated considerations across the three dimensions, as a framework for reasoning about the documentation contribution process. This framework can inform information seeking as well as documentation creation tools about the context in which documentation was contributed.

2024-12-11

ArXiv (preprint)

doi.org

arxiv.org

4+3 Phases of Compute-Optimal Neural Scaling Laws

Elliot Paquette

Courtney Paquette

Lechao Xiao

Jeffrey Pennington

We consider the solvable neural scaling model with three parameters: data complexity, target complexity, and model-parameter-count. We use t… (see more)his neural scaling model to derive new predictions about the compute-limited, infinite-data scaling law regime. To train the neural scaling model, we run one-pass stochastic gradient descent on a mean-squared loss. We derive a representation of the loss curves which holds over all iteration counts and improves in accuracy as the model parameter count grows. We then analyze the compute-optimal model-parameter-count, and identify 4 phases (+3 subphases) in the data-complexity/target-complexity phase-plane. The phase boundaries are determined by the relative importance of model capacity, optimizer noise, and embedding of the features. We furthermore derive, with mathematical proof and extensive numerical evidence, the scaling-law exponents in all of these phases, in particular computing the optimal model-parameter-count as a function of floating point operation budget.

2024-12-10

Conference on Neural Information Processing Systems (Accept (spotlight))

doi.org

openreview.net

Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning

Harley Wiltzer

Bellemare Marc-Emmanuel

David Meger

Patrick Shafto

Yash Jhaveri

When decisions are made at high frequency, traditional reinforcement learning (RL) methods struggle to accurately estimate action values. In… (see more) turn, their performance is inconsistent and often poor. Whether the performance of distributional RL (DRL) agents suffers similarly, however, is unknown. In this work, we establish that DRL agents are sensitive to the decision frequency. We prove that action-conditioned return distributions collapse to their underlying policy's return distribution as the decision frequency increases. We quantify the rate of collapse of these return distributions and exhibit that their statistics collapse at different rates. Moreover, we define distributional perspectives on action gaps and advantages. In particular, we introduce the superiority as a probabilistic generalization of the advantage -- the core object of approaches to mitigating performance issues in high-frequency value-based RL. In addition, we build a superiority-based DRL algorithm. Through simulations in an option-trading domain, we validate that proper modeling of the superiority distribution produces improved controllers at high decision frequencies.

2024-12-10

Conference on Neural Information Processing Systems (Accept (poster))

doi.org

openreview.net

Adaptive Exploration for Data-Efficient General Value Function Evaluations

Arushi Jain

Josiah P. Hanna

Doina Precup

General Value Functions (GVFs) (Sutton et al., 2011) represent predictive knowledge in reinforcement learning. Each GVF computes the expecte… (see more)d return for a given policy, based on a unique reward. Existing methods relying on fixed behavior policies or pre-collected data often face data efficiency issues when learning multiple GVFs in parallel using off-policy methods. To address this, we introduce GVFExplorer, which adaptively learns a single behavior policy that efficiently collects data for evaluating multiple GVFs in parallel. Our method optimizes the behavior policy by minimizing the total variance in return across GVFs, thereby reducing the required environmental interactions. We use an existing temporal-difference-style variance estimator to approximate the return variance. We prove that each behavior policy update decreases the overall mean squared error in GVF predictions. We empirically show our method's performance in tabular and nonlinear function approximation settings, including Mujoco environments, with stationary and non-stationary reward signals, optimizing data usage and reducing prediction errors across multiple GVFs.

2024-12-10

Conference on Neural Information Processing Systems (Accept (poster))

doi.org

openreview.net

Balancing Context Length and Mixing Times for Reinforcement Learning at Scale

Matthew Riemer

Khimya Khetarpal

Janarthanan Rajendran

Sarath Chandar

Due to the recent remarkable advances in artiﬁcial intelligence, researchers have begun to consider challenging learning problems such as … (see more)learning to generalize behavior from large ofﬂine datasets or learning online in non-Markovian environments. Meanwhile, recent advances in both of these areas have increasingly relied on conditioning policies on large context lengths. A natural question is if there is a limit to the performance beneﬁts of increasing the context length if the computation needed is available. In this work, we establish a novel theoretical result that links the context length of a policy to the time needed to reliably evaluate its performance (i.e., its mixing time) in large scale partially observable reinforcement learning environments that exhibit latent sub-task structure. This analysis underscores a key tradeoff: when we extend the context length, our policy can more effectively model non-Markovian dependencies, but this comes at the cost of potentially slower policy evaluation and as a result slower downstream learning. Moreover, our empirical results highlight the relevance of this analysis when leveraging Transformer based neural networks. This perspective will become increasingly pertinent as the ﬁeld scales towards larger and more realistic environments, opening up a number of potential future directions for improving the way we design learning agents.

2024-12-10

Neural Information Processing Systems (Accept (poster))

doi.org

openreview.net

CALE: Continuous Arcade Learning Environment

Jesse Farebrother

Pablo Samuel Castro

We introduce the Continuous Arcade Learning Environment (CALE), an extension of the well-known Arcade Learning Environment (ALE) [Bellemare … (see more)et al., 2013]. The CALE uses the same underlying emulator of the Atari 2600 gaming system (Stella), but adds support for continuous actions. This enables the benchmarking and evaluation of continuous-control agents (such as PPO [Schulman et al., 2017] and SAC [Haarnoja et al., 2018]) and value-based agents (such as DQN [Mnih et al., 2015] and Rainbow [Hessel et al., 2018]) on the same environment suite. We provide a series of open questions and research directions that CALE enables, as well as initial baseline results using Soft Actor-Critic. CALE is available as part of the ALE athttps://github.com/Farama-Foundation/Arcade-Learning-Environment.

2024-12-10

NEURIPS (Accept (Poster))

doi.org

openreview.net

Cell ontology guided transcriptome foundation model

Manqi Zhou

Boyu Han

Transcriptome foundation models (TFMs) hold great promises of deciphering the transcriptomic language that dictate diverse cell functions by… (see more) self-supervised learning on large-scale single-cell gene expression data, and ultimately unraveling the complex mechanisms of human diseases. However, current TFMs treat cells as independent samples and ignore the taxonomic relationships between cell types, which are available in cell ontology graphs. We argue that effectively leveraging this ontology information during the TFM pre-training can improve learning biologically meaningful gene co-expression patterns while preserving TFM as a general purpose foundation model for downstream zero-shot and fine-tuning tasks. To this end, we present **s**ingle **c**ell, **Cell**-**o**ntology guided TFM (scCello). We introduce cell-type coherence loss and ontology alignment loss, which are minimized along with the masked gene expression prediction loss during the pre-training. The novel loss component guide scCello to learn the cell-type-specific representation and the structural relation between cell types from the cell ontology graph, respectively. We pre-trained scCello on 22 million cells from CellxGene database leveraging their cell-type labels mapped to the cell ontology graph from Open Biological and Biomedical Ontology Foundry. Our TFM demonstrates competitive generalization and transferability performance over the existing TFMs on biologically important tasks including identifying novel cell types of unseen cells, prediction of cell-type-specific marker genes, and cancer drug responses. Source code and model weights are available at https://github.com/DeepGraphLearning/scCello.

2024-12-10

Neural Information Processing Systems (Accept (spotlight))

doi.org

openreview.net

Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval

Haolun Wu

Ofer Meshi

Masrour Zoghi

Fernando Diaz

Xue Liu

Craig Boutilier

Maryam Karimzadehgan

Accurate modeling of the diverse and dynamic interests of users remains a significant challenge in the design of personalized recommender sy… (see more)stems. Existing user modeling methods, like single-point and multi-point representations, have limitations w.r.t.\ accuracy, diversity, and adaptability. To overcome these deficiencies, we introduce density-based user representations (DURs), a novel method that leverages Gaussian process regression (GPR) for effective multi-interest recommendation and retrieval. Our approach, GPR4DUR, exploits DURs to capture user interest variability without manual tuning, incorporates uncertainty-awareness, and scales well to large numbers of users. Experiments using real-world offline datasets confirm the adaptability and efficiency of GPR4DUR, while online experiments with simulated users demonstrate its ability to address the exploration-exploitation trade-off by effectively utilizing model uncertainty.

2024-12-10

Conference on Neural Information Processing Systems (Accept (poster))

doi.org

openreview.net

Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling

Yuanqi Du

Michael Plainer

Rob Brekelmans

Chenru Duan

Frank Noé

Carla P. Gomes

Alán Aspuru-Guzik

Kirill Neklyudov

Rare event sampling in dynamical systems is a fundamental problem arising in the natural sciences, which poses significant computational cha… (see more)llenges due to an exponentially large space of trajectories. For settings where the dynamical system of interest follows a Brownian motion with known drift, the question of conditioning the process to reach a given endpoint or desired rare event is definitively answered by Doob's h-transform. However, the naive estimation of this transform is infeasible, as it requires simulating sufficiently many forward trajectories to estimate rare event probabilities. In this work, we propose a variational formulation of Doob's h-transform as an optimization problem over trajectories between a given initial point and the desired ending point. To solve this optimization, we propose a simulation-free training objective with a model parameterization that imposes the desired boundary conditions by design. Our approach significantly reduces the search space over trajectories and avoids expensive trajectory simulation and inefficient importance sampling estimators which are required in existing methods. We demonstrate the ability of our method to find feasible transition paths on real-world molecular simulation and protein folding tasks.

2024-12-10

Conference on Neural Information Processing Systems (Accept (spotlight))

doi.org

openreview.net

Efficient Adversarial Training in LLMs with Continuous Attacks

Stephan Günnemann

Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. In many domains, adversarial tra… (see more)ining has proven to be one of the most promising methods to reliably improve robustness against such attacks. Yet, in the context of LLMs, current methods for adversarial training are hindered by the high computational costs required to perform discrete adversarial attacks at each training iteration. We address this problem by instead calculating adversarial attacks in the continuous embedding space of the LLM, which is orders of magnitudes more efficient. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses: the first makes the model robust on continuous embedding attacks computed on an adversarial behaviour dataset; the second ensures the usefulness of the final model by fine-tuning on utility data. Moreover, we introduce C-AdvIPO, an adversarial variant of IPO that does not require utility data for adversarially robust alignment. Our empirical evaluation on five models from different families (Gemma, Phi3, Mistral, Zephyr, Llama2) and at different scales (2B, 3.8B, 7B) shows that both algorithms substantially enhance LLM robustness against discrete attacks (GCG, AutoDAN, PAIR), while maintaining utility. Our results demonstrate that robustness to continuous perturbations can extrapolate to discrete threat models. Thereby, we present a path toward scalable adversarial training algorithms for robustly aligning LLMs.

2024-12-10

Conference on Neural Information Processing Systems (Accept (spotlight))

doi.org

openreview.net

Efficient Leverage Score Sampling for Tensor Train Decomposition

Vivek Bharadwaj

Beheshteh T. Rakhshan

Osman Asif Malik

Guillaume Rabusseau

Tensor Train~(TT) decomposition is widely used in the machine learning and quantum physics communities as a popular tool to efficiently comp… (see more)ress high-dimensional tensor data. In this paper, we propose an efficient algorithm to accelerate computing the TT decomposition with the Alternating Least Squares (ALS) algorithm relying on exact leverage scores sampling. For this purpose, we propose a data structure that allows us to efficiently sample from the tensor with time complexity logarithmic in the tensor size. Our contribution specifically leverages the canonical form of the TT decomposition. By maintaining the canonical form through each iteration of ALS, we can efficiently compute (and sample from) the leverage scores, thus achieving significant speed-up in solving each sketched least-square problem. Experiments on synthetic and real data on dense and sparse tensors demonstrate that our method outperforms SVD-based and ALS-based algorithms.

2024-12-10

Conference on Neural Information Processing Systems (Accept (poster))

doi.org

openreview.net

Efficient Reinforcement Learning by Discovering Neural Pathways

Samin Yeasar Arnob

Riyasat Ohib

Sergey Plis

Amy Zhang

Alessandro Sordoni

Doina Precup

2024-12-10