论文检索

Miscellaneous Aspects of Machine Learning · Causality

Undral Byambadalai, Tatsushi Oka, Shota Yasui

We propose a novel regression adjustment method designed for estimating distributional treatment effect parameters in randomized experiments. Randomized experiments have been extensively used to estimate treatment effects in various scientific fields. However, to gain deeper insights, it is essential to estimate distributional treatment effects rather than relying solely on average effects. Our approach incorporates pre-treatment covariates into a distributional regression framework, utilizing machine learning techniques to improve the precision of distributional treatment effect estimators. The proposed approach can be readily implemented with off-the-shelf machine learning methods and remains valid as long as the nuisance components are reasonably well estimated. Also, we establish the asymptotic properties of the proposed estimator and present a uniformly valid inference method. Through simulation results and real data analysis, we demonstrate the effectiveness of integrating machine learning techniques in reducing the variance of distributional treatment effect estimators in finite samples.

Reinforcement Learning

Youngsoo Jang, Geon-Hyeong Kim, Byoungjip Kim, Yu Jin Kim, Honglak Lee, Moontae Lee

As the pre-training objectives (e.g., next token prediction) of language models (LMs) are inherently not aligned with task scores, optimizing LMs to achieve higher downstream task scores is essential. One of the promising approaches is to fine-tune LMs through reinforcement learning (RL). However, conventional RL methods based on PPO and a penalty of KL divergence are vulnerable to text degeneration where LMs do not generate natural texts anymore after RL fine-tuning. To address this problem, we provide Degeneration-free Policy Optimization (DfPO) that can fine-tune LMs to generate texts that achieve improved downstream task scores, while preserving the ability to generate natural texts. To achieve this, we introduce KL-masking which masks out the actions that potentially cause deviation from the reference policy when its likelihood is increased or decreased. Then, we devise truncated advantage functions for separately performing likelihood maximization and minimization to improve the task performance. In the experiments, we provide the results of DfPO and baseline algorithms on various generative NLP tasks including text continuation, text detoxification, and commonsense generation. Our experiments demonstrate that DfPO successfully improves the downstream task scores while preserving the ability to generate natural texts, without requiring additional hyperparameter search.

Social Aspects · Fairness, Equity, Justice and Safety

Guy Horowitz, Yonatan Sommer, Moran Koren, Nir Rosenfeld

When users stand to gain from certain predictive outcomes, they are prone to act strategically to obtain predictions that are favorable. Most current works consider strategic behavior that manifests as users modifying their features; instead, we study a novel setting in which users decide whether to even participate (or not), this in response to the learned classifier. Considering learning approaches of increasing strategic awareness, we investigate the effects of user self-selection on learning, and the implications of learning on the composition of the self-selected population. Building on this, we propose a differentiable framework for learning under self-selective behavior, which can be optimized effectively. We conclude with experiments on real data and simulated behavior that complement our analysis and demonstrate the utility of our approach.

Theory · Online Learning and Bandits

Yassir Jedra, William Réveillard, Stefan Stojanovic, Alexandre Proutiere

We study contextual bandits with low-rank structure where, in each round, if the (context, arm) pair $(i,j)\in [m]\times [n]$ is selected, the learner observes a noisy sample of the $(i,j)$-th entry of an unknown low-rank reward matrix. Successive contexts are generated randomly in an i.i.d. manner and are revealed to the learner. For such bandits, we present efficient algorithms for policy evaluation, best policy identification and regret minimization. For policy evaluation and best policy identification, we show that our algorithms are nearly minimax optimal. For instance, the number of samples required to return an $\varepsilon$-optimal policy with probability at least $1-\delta$ typically scales as $\frac{m+n}{\varepsilon^2}\log(1/\delta)$. Our regret minimization algorithm enjoys minimax guarantees typically scaling as $r^{5/4}(m+n)^{3/4}\sqrt{T}$, which improves over existing algorithms. All the proposed algorithms consist of two phases: they first leverage spectral methods to estimate the left and right singular subspaces of the low-rank reward matrix. We show that these estimates enjoy tight error guarantees in the two-to-infinity norm. This in turn allows us to reformulate our problems as a misspecified linear bandit problem with dimension roughly $r(m+n)$ and misspecification controlled by the subspace recovery error, as well as to design the second phase of our algorithms efficiently.

Deep Learning · Large Language Models

Qinyuan Cheng, Tianxiang Sun, Xiangyang Liu, Wenwei Zhang, Zhangyue Yin, Shimin Li, Linyang Li, Zhengfu He, Kai Chen, Xipeng Qiu

AI assistants powered by Large Language Models (LLMs) have demonstrated impressive performance in various tasks. However, LLMs still make factual errors in knowledge-intensive tasks such as open-domain question answering. These untruthful responses from AI assistants can pose significant risks in practical applications. Therefore, in this paper, we ask the question **Can AI assistants know what they don't know and express this awareness through natural language?** To investigate this, we construct a model-specific "I don't know" (Idk) dataset. This dataset includes Supervised Fine-tuning data and preference data, categorizing questions based on whether the assistant knows or does not know the answers. Then, we align the assistant with its corresponding Idk dataset using different alignment methods, including Supervised Fine-tuning and preference optimization. Experimental results show that, after alignment with the Idk dataset, the assistant is more capable of declining to answer questions outside its knowledge scope. The assistant aligned with the Idk dataset shows significantly higher truthfulness than the original assistant.

Applications · Everything Else

Xudong Li, Timin Gao, Runze Hu, Yan Zhang, Shengchuan Zhang, Xiawu Zheng, Jingyuan Zheng, Yunhang Shen, Ke Li, Yutao Liu 等

The current state-of-the-art No-Reference Image Quality Assessment (NR-IQA) methods typically rely on feature extraction from upstream semantic backbone networks, assuming that all extracted features are relevant. However, we make a key observation that not all features are beneficial, and some may even be harmful, necessitating careful selection. Empirically, we find that many image pairs with small feature spatial distances can have vastly different quality scores, indicating that the extracted features may contain quality-irrelevant noise. To address this issue, we propose a Quality-Aware Feature Matching IQA Metric (QFM-IQM) that employs an adversarial perspective to remove harmful semantic noise features from the upstream task. Specifically, QFM-IQM enhances the semantic noise distinguish capabilities by matching image pairs with similar quality scores but varying semantic features as adversarial semantic noise and adaptively adjusting the upstream task’s features by reducing sensitivity to adversarial noise perturbation. Furthermore, we utilize a distillation framework to expand the dataset and improve the model's generalization ability. Extensive experiments conducted on eight standard IQA datasets have demonstrated the effectiveness of our proposed QFM-IQM.

Applications

Xudong Li, Runze Hu, Jingyuan Zheng, Yan Zhang, Shengchuan Zhang, Xiawu Zheng, Ke Li, Yunhang Shen, Yutao Liu, Pingyang Dai 等

Blind Image Quality Assessment (BIQA) mirrors subjective made by human observers. Generally, humans favor comparing relative qualities over predicting absolute qualities directly. However, current BIQA models focus on mining the "local" context, i.e., the relationship between information among individual images and the absolute quality of the image, ignoring the "global" context of the relative quality contrast among different images in the training data. In this paper, we present the Perceptual Context and Sensitivity BIQA (CSIQA), a novel contrastive learning paradigm that seamlessly integrates "global'' and "local'' perspectives into the BIQA. Specifically, the CSIQA comprises two primary components: 1) A Quality Context Contrastive Learning module, which is equipped with different contrastive learning strategies to effectively capture potential quality correlations in the global context of the dataset. 2) A Quality-aware Mask Attention Module, which employs the random mask to ensure the consistency with visual local sensitivity, thereby improving the model's perception of local distortions. Extensive experiments on eight standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods.

Applications · Genetics, Cell Biology, etc

Yair Schiff, Chia Hsiang Kao, Aaron Gokaslan, Tri Dao, Albert Gu, Volodymyr Kuleshov

Large-scale sequence modeling has sparked rapid advances that now extend into biology and genomics. However, modeling genomic sequences introduces challenges such as the need to model long-range token interactions, the effects of upstream and downstream regions of the genome, and the reverse complementarity (RC) of DNA. Here, we propose an architecture motivated by these challenges that builds off the long-range Mamba block, and extends it to a BiMamba component that supports bi-directionality, and to a MambaDNA block that additionally supports RC equivariance. We use MambaDNA as the basis of Caduceus, the first family of RC equivariant bi-directional long-range DNA language models, and we introduce pre-training and fine-tuning strategies that yield Caduceus DNA foundation models. Caduceus outperforms previous long-range models on downstream benchmarks; on a challenging long-range variant effect prediction task, Caduceus exceeds the performance of 10x larger models that do not leverage bi-directionality or equivariance. Code to reproduce our experiments is available here: https://github.com/kuleshov-group/caduceus.

Miscellaneous Aspects of Machine Learning · Supervised Learning

Kun Song, Zhiquan Tan, Bochao Zou, Huimin Ma, Weiran Huang

In this paper, we use matrix information theory as an analytical tool to analyze the dynamics of the information interplay between data representations and classification head vectors in the supervised learning process. Specifically, inspired by the theory of Neural Collapse, we introduce matrix mutual information ratio (MIR) and matrix entropy difference ratio (HDR) to assess the interactions of data representation and class classification heads in supervised learning, and we determine the theoretical optimal values for MIR and HDR when Neural Collapse happens. Our experiments show that MIR and HDR can effectively explain many phenomena occurring in neural networks, for example, the standard supervised training dynamics, linear mode connectivity, and the performance of label smoothing and pruning. Additionally, we use MIR and HDR to gain insights into the dynamics of grokking, which is an intriguing phenomenon observed in supervised training, where the model demonstrates generalization capabilities long after it has learned to fit the training data. Furthermore, we introduce MIR and HDR as loss terms in supervised and semi-supervised learning to optimize the information interactions among samples and classification heads. The empirical results provide evidence of the method's effectiveness, demonstrating that the utilization of MIR and HDR not only aids in comprehending the dynamics throughout the training process but can also enhances the training procedure itself.

Deep Learning · Large Language Models

Xiang Cheng, Yuxin Chen, Suvrit Sra

Many neural network architectures are known to be Turing Complete, and can thus, in principle implement arbitrary algorithms. However, Transformers are unique in that they can implement gradient-based learning algorithms *under simple parameter configurations*. This paper provides theoretical and empirical evidence that (non-linear) Transformers naturally learn to implement gradient descent *in function space*, which in turn enable them to learn non-linear functions in context. Our results apply to a broad class of combinations of non-linear architectures and non-linear in-context learning tasks. Additionally, we show that the optimal choice of non-linear activation depends in a natural way on the class of functions that need to be learned.

Deep Learning · Generative Models and Autoencoders

Heli Ben-Hamu, Omri Puny, Itai Gat, Brian Karrer, Uriel Singer, Yaron Lipman

Taming the generation outcome of state of the art Diffusion and Flow-Matching (FM) models without having to re-train a task-specific model unlocks a powerful tool for solving inverse problems, conditional generation, and controlled generation in general. In this work we introduce *D-Flow*, a simple framework for controlling the generation process by differentiating through the flow, optimizing for the source (noise) point. We motivate this framework by our key observation stating that for Diffusion/FM models trained with Gaussian probability paths, differentiating through the generation process projects gradient on the data manifold, implicitly injecting the prior into the optimization process. We validate our framework on linear and non-linear controlled generation problems including: image and audio inverse problems and conditional molecule generation reaching state of the art performance across all.

Deep Learning · Large Language Models

Ziqian Lin, Kangwook Lee

In-context learning (ICL) exhibits dual operating modes: ***task learning***, i.e., acquiring a new skill from in-context samples, and ***task retrieval***, i.e., locating and activating a relevant pretrained skill. Recent theoretical work proposes various mathematical models to analyze ICL, but they cannot fully explain the duality. In this work, we analyze a generalized probabilistic model for pretraining data, obtaining a quantitative understanding of the two operating modes of ICL. Leveraging our analysis, we provide the first explanation of an unexplained phenomenon observed with real-world large language models (LLMs). Under some settings, the ICL risk initially increases and then decreases with more in-context examples. Our analysis offers a plausible explanation for this "early ascent" phenomenon: a limited number of in-context samples may lead to the retrieval of an incorrect skill, thereby increasing the risk, which will eventually diminish as task learning takes effect with more in-context samples. We also analyze ICL with biased labels, e.g., zero-shot ICL, where in-context examples are assigned random labels, and predict the bounded efficacy of such approaches. We corroborate our analysis and predictions with extensive experiments with Transformers and LLMs.

Deep Learning · Generative Models and Autoencoders

Arsalan Motamedi, Pooya Ronagh

Gibbs sampling from continuous real-valued functions is a challenging problem of interest in machine learning. Here we leverage quantum Fourier transforms to build a quantum algorithm for this task when the function is periodic. We use the quantum algorithms for solving linear ordinary differential equations to solve the Fokker–Planck equation and prepare a quantum state encoding the Gibbs distribution. We show that the efficiency of interpolation and differentiation of these functions on a quantum computer depends on the rate of decay of the Fourier coefficients of the Fourier transform of the function. We view this property as a concentration of measure in the Fourier domain, and also provide functional analytic conditions for it. Our algorithm makes zeroeth order queries to a quantum oracle of the function and achieves polynomial quantum speedups in mean estimation in the Gibbs measure for generic non-convex periodic functions. At high temperatures the algorithm also allows for exponentially improved precision in sampling from Morse functions.

Applications · Computer Vision

R. Kenny Jones, Siddhartha Chaudhuri, Daniel Ritchie

People grasp flexible visual concepts from a few examples. We explore a neurosymbolic system that learns how to infer programs that capture visual concepts in a domain-general fashion. We introduce Template Programs: programmatic expressions from a domain-specific language that specify structural and parametric patterns common to an input concept. Our framework supports multiple concept-related tasks, including few-shot generation and co-segmentation through parsing. We develop a learning paradigm that allows us to train networks that infer Template Programs directly from visual datasets that contain concept groupings. We run experiments across multiple visual domains: 2D layouts, Omniglot characters, and 3D shapes. We find that our method outperforms task-specific alternatives, and performs competitively against domain-specific approaches for the limited domains where they exist.

Social Aspects · Accountability, Transparency and Interpretability

Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova, Hamid Kazemi, Aniruddha Saha, Micah Goldblum, Jonas Geiping, Tom Goldstein

Detecting text generated by modern large language models is thought to be hard, as both LLMs and humans can exhibit a wide range of complex behaviors. However, we find that a score based on contrasting two closely related language models is highly accurate at separating human-generated and machine-generated text. Based on this mechanism, we propose a novel LLM detector that only requires simple calculations using a pair of pre-trained LLMs. The method, called *Binoculars*, achieves state-of-the-art accuracy without any training data. It is capable of spotting machine text from a range of modern LLMs without any model-specific modifications. We comprehensively evaluate *Binoculars* on a number of text sources and in varied situations. Over a wide range of document types, *Binoculars* detects over 90% of generated samples from ChatGPT (and other LLMs) at a false positive rate of 0.01%, despite not being trained on any ChatGPT data. Code available at https://github.com/ahans30/Binoculars.

Reinforcement Learning · Multi-agent

Long Ma, Yuanfei Wang, Fangwei Zhong, Song-Chun Zhu, Yizhou Wang

Fast adapting to unknown peers (partners or opponents) with different strategies is a key challenge in multi-agent games. To do so, it is crucial for the agent to probe and identify the peer’s strategy efficiently, as this is the prerequisite for carrying out the best response in adaptation. However, exploring the strategies of unknown peers is difficult, especially when the games are partially observable and have a long horizon. In this paper, we propose a peer identification reward, which rewards the learning agent based on how well it can identify the behavior pattern of the peer over the historical context, such as the observation over multiple episodes. This reward motivates the agent to learn a context-aware policy for effective exploration and fast adaptation, i.e., to actively seek and collect informative feedback from peers when uncertain about their policies and to exploit the context to perform the best response when confident. We evaluate our method on diverse testbeds that involve competitive (Kuhn Poker), cooperative (PO-Overcooked), or mixed (Predator-Prey-W) games with peer agents. We demonstrate that our method induces more active exploration behavior, achieving faster adaptation and better outcomes than existing methods.

Reinforcement Learning · Function Approximation

Uri Sherman, Alon Cohen, Tomer Koren, Yishay Mansour

We study regret minimization in online episodic linear Markov Decision Processes, and propose a policy optimization algorithm that is computationally efficient, and obtains rate optimal $\widetilde O (\sqrt K)$ regret where $K$ denotes the number of episodes. Our work is the first to establish the optimal rate (in terms of $K$) of convergence in the stochastic setting with bandit feedback using a policy optimization based approach, and the first to establish the optimal rate in the adversarial setup with full information feedback, for which no algorithm with an optimal rate guarantee was previously known.

Applications · Chemistry and Drug Discovery

Agustinus Kristiadi, Felix Strieth-Kalthoff, Marta Skreta, Pascal Poupart, Alan Aspuru-Guzik, Geoff Pleiss

Automation is one of the cornerstones of contemporary material discovery. Bayesian optimization (BO) is an essential part of such workflows, enabling scientists to leverage prior domain knowledge into efficient exploration of a large molecular space. While such prior knowledge can take many forms, there has been significant fanfare around the ancillary scientific knowledge encapsulated in large language models (LLMs). However, existing work thus far has only explored LLMs for heuristic materials searches. Indeed, recent work obtains the uncertainty estimate---an integral part of BO---from point-estimated, _non-Bayesian_ LLMs. In this work, we study the question of whether LLMs are actually useful to accelerate principled _Bayesian_ optimization in the molecular space. We take a sober, dispassionate stance in answering this question. This is done by carefully (i) viewing LLMs as fixed feature extractors for standard but principled BO surrogate models and by (ii) leveraging parameter-efficient finetuning methods and Bayesian neural networks to obtain the posterior of the LLM surrogate. Our extensive experiments with real-world chemistry problems show that LLMs can be useful for BO over molecules, but only if they have been pretrained or finetuned with domain-specific data.

Deep Learning · Everything Else

Jinsoo Yoo, Yunpeng Liu, Frank Wood, Geoff Pleiss

In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on past data. Our work demonstrates a limitation of this approach: neural networks trained with experience replay tend to have unstable optimization trajectories, impeding their overall accuracy. Surprisingly, these instabilities persist even when the replay buffer stores all previous training examples, suggesting that this issue is orthogonal to catastrophic forgetting. We minimize these instabilities through a simple modification of the optimization geometry. Our solution, Layerwise Proximal Replay (LPR), balances learning from new and replay data while only allowing for gradual changes in the hidden activation of past data. We demonstrate that LPR consistently improves replay-based online continual learning across multiple problem settings, regardless of the amount of available replay memory.

Theory · Probabilistic Methods

Johannes Resin

In the face of uncertainty, the need for probabilistic assessments has long been recognized in the literature on forecasting. In classification, however, comparative evaluation of classifiers often focuses on predictions specifying a single class through the use of simple accuracy measures, which disregard any probabilistic uncertainty quantification. I propose probabilistic top lists as a novel type of prediction in classification, which bridges the gap between single-class predictions and predictive distributions. The probabilistic top list functional is elicitable through the use of strictly consistent evaluation metrics. The proposed evaluation metrics are based on symmetric proper scoring rules and admit comparison of various types of predictions ranging from single-class point predictions to fully specified predictive distributions. The Brier score yields a metric that is particularly well suited for this kind of comparison.