Searcharxiv⌕ Search

arXiv subjects

Zhao Song

Publications and source records attributed to Zhao Song.

At least 199 records · Page 11Linked to original sources
arXiv2023

Exit options sustain altruistic punishment and decrease the second-order free-riders, but it is not a panacea

Altruistic punishment, where individuals incur personal costs to punish others who have harmed third parties, presents an evolutionary conundrum as it undermines individual fitness. Resolving this puzzle is crucial for understanding the emergence and maintenance of human cooperation. This study investigates the role of an alternative strategy, the exit option, in explaining altruistic punishment. We analyze a two-stage prisoner's dilemma game in well-mixed and networked populations, considering both finite and infinite scenarios. Our findings reveal that the exit option does not significantly enhance altruistic punishment in well-mixed populations. However, in networked populations, the exit option enables the existence of altruistic punishment and gives rise to complex dynamics, including cyclic dominance and bi-stable states. This research contributes to our understanding of costly punishment and sheds light on the effectiveness of different voluntary participation strategies in addressing the conundrum of punishment.

q-bio.PE↗
arXiv2023

Zero-th Order Algorithm for Softmax Attention Optimization

Large language models (LLMs) have brought about significant transformations in human society. Among the crucial computations in LLMs, the softmax unit holds great importance. Its helps the model generating a probability distribution on potential subsequent words or phrases, considering a series of input words. By utilizing this distribution, the model selects the most probable next word or phrase, based on the assigned probabilities. The softmax unit assumes a vital function in LLM training as it facilitates learning from data through the adjustment of neural network weights and biases. With the development of the size of LLMs, computing the gradient becomes expensive. However, Zero-th Order method can approximately compute the gradient with only forward passes. In this paper, we present a Zero-th Order algorithm specifically tailored for Softmax optimization. We demonstrate the convergence of our algorithm, highlighting its effectiveness in efficiently computing gradients for large-scale LLMs. By leveraging the Zeroth-Order method, our work contributes to the advancement of optimization techniques in the context of complex language models.

cs.LG↗
arXiv2023

Efficient SGD Neural Network Training via Sublinear Activated Neuron Identification

Deep learning has been widely used in many fields, but the model training process usually consumes massive computational resources and time. Therefore, designing an efficient neural network training method with a provable convergence guarantee is a fundamental and important research question. In this paper, we present a static half-space report data structure that consists of a fully connected two-layer neural network for shifted ReLU activation to enable activated neuron identification in sublinear time via geometric search. We also prove that our algorithm can converge in $O(M^2/ε^2)$ time with network size quadratic in the coefficient norm upper bound $M$ and error term $ε$.

cs.LG↗
arXiv2023

In-Context Learning for Attention Scheme: from Single Softmax Regression to Multiple Softmax Regression via a Tensor Trick

Large language models (LLMs) have brought significant and transformative changes in human society. These models have demonstrated remarkable capabilities in natural language understanding and generation, leading to various advancements and impacts across several domains. We consider the in-context learning under two formulation for attention related regression in this work. Given matrices $A_1 \in \mathbb{R}^{n \times d}$, and $A_2 \in \mathbb{R}^{n \times d}$ and $B \in \mathbb{R}^{n \times n}$, the purpose is to solve some certain optimization problems: Normalized version $\min_{X} \| D(X)^{-1} \exp(A_1 X A_2^\top) - B \|_F^2$ and Rescaled version $\| \exp(A_1 X A_2^\top) - D(X) \cdot B \|_F^2$. Here $D(X) := \mathrm{diag}( \exp(A_1 X A_2^\top) {\bf 1}_n )$. Our regression problem shares similarities with previous studies on softmax-related regression. Prior research has extensively investigated regression techniques related to softmax regression: Normalized version $\| \langle \exp(Ax) , {\bf 1}_n \rangle^{-1} \exp(Ax) - b \|_2^2$ and Resscaled version $\| \exp(Ax) - \langle \exp(Ax), {\bf 1}_n \rangle b \|_2^2 $ In contrast to previous approaches, we adopt a vectorization technique to address the regression problem in matrix formulation. This approach expands the dimension from $d$ to $d^2$, resembling the formulation of the regression problem mentioned earlier. Upon completing the lipschitz analysis of our regression function, we have derived our main result concerning in-context learning.

cs.LG↗
arXiv2023

Efficient Algorithm for Solving Hyperbolic Programs

Hyperbolic polynomials is a class of real-roots polynomials that has wide range of applications in theoretical computer science. Each hyperbolic polynomial also induces a hyperbolic cone that is of particular interest in optimization due to its generality, as by choosing the polynomial properly, one can easily recover the classic optimization problems such as linear programming and semidefinite programming. In this work, we develop efficient algorithms for hyperbolic programming, the problem in each one wants to minimize a linear objective, under a system of linear constraints and the solution must be in the hyperbolic cone induced by the hyperbolic polynomial. Our algorithm is an instance of interior point method (IPM) that, instead of following the central path, it follows the central Swath, which is a generalization of central path. To implement the IPM efficiently, we utilize a relaxation of the hyperbolic program to a quadratic program, coupled with the first four moments of the hyperbolic eigenvalues that are crucial to update the optimization direction. We further show that, given an evaluation oracle of the polynomial, our algorithm only requires $O(n^2d^{2.5})$ oracle calls, where $n$ is the number of variables and $d$ is the degree of the polynomial, with extra $O((n+m)^3 d^{0.5})$ arithmetic operations, where $m$ is the number of constraints.

math.OC↗
arXiv2023

InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding

Soft prompt tuning achieves superior performances across a wide range of few-shot tasks. However, the performances of prompt tuning can be highly sensitive to the initialization of the prompts. We also empirically observe that conventional prompt tuning methods cannot encode and learn sufficient task-relevant information from prompt tokens. In this work, we develop an information-theoretic framework that formulates soft prompt tuning as maximizing mutual information between prompts and other model parameters (or encoded representations). This novel view helps us to develop a more efficient, accurate and robust soft prompt tuning method InfoPrompt. With this framework, we develop two novel mutual information based loss functions, to (i) discover proper prompt initialization for the downstream tasks and learn sufficient task-relevant information from prompt tokens and (ii) encourage the output representation from the pretrained language model to be more aware of the task-relevant information captured in the learnt prompt. Extensive experiments validate that InfoPrompt can significantly accelerate the convergence of the prompt tuning and outperform traditional prompt tuning methods. Finally, we provide a formal theoretical result for showing to show that gradient descent type algorithm can be used to train our mutual information loss.

cs.CL↗
arXiv2023

Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability

Sketching is one of the most fundamental tools in large-scale machine learning. It enables runtime and memory saving via randomly compressing the original large problem into lower dimensions. In this paper, we propose a novel sketching scheme for the first order method in large-scale distributed learning setting, such that the communication costs between distributed agents are saved while the convergence of the algorithms is still guaranteed. Given gradient information in a high dimension $d$, the agent passes the compressed information processed by a sketching matrix $R\in \mathbb{R}^{s\times d}$ with $s\ll d$, and the receiver de-compressed via the de-sketching matrix $R^\top$ to ``recover'' the information in original dimension. Using such a framework, we develop algorithms for federated learning with lower communication costs. However, such random sketching does not protect the privacy of local data directly. We show that the gradient leakage problem still exists after applying the sketching technique by presenting a specific gradient attack method. As a remedy, we prove rigorously that the algorithm will be differentially private by adding additional random noises in gradient information, which results in a both communication-efficient and differentially private first order approach for federated learning tasks. Our sketching scheme can be further generalized to other learning settings and might be of independent interest itself.

cs.LG↗
arXiv2023

Query Complexity of Active Learning for Function Family With Nearly Orthogonal Basis

Many machine learning algorithms require large numbers of labeled data to deliver state-of-the-art results. In applications such as medical diagnosis and fraud detection, though there is an abundance of unlabeled data, it is costly to label the data by experts, experiments, or simulations. Active learning algorithms aim to reduce the number of required labeled data points while preserving performance. For many convex optimization problems such as linear regression and $p$-norm regression, there are theoretical bounds on the number of required labels to achieve a certain accuracy. We call this the query complexity of active learning. However, today's active learning algorithms require the underlying learned function to have an orthogonal basis. For example, when applying active learning to linear regression, the requirement is the target function is a linear composition of a set of orthogonal linear functions, and active learning can find the coefficients of these linear functions. We present a theoretical result to show that active learning does not need an orthogonal basis but rather only requires a nearly orthogonal basis. We provide the corresponding theoretical proofs for the function family of nearly orthogonal basis, and its applications associated with the algorithmically efficient active learning framework.

cs.LG↗
arXiv2023

A Mathematical Abstraction for Balancing the Trade-off Between Creativity and Reality in Large Language Models

Large Language Models have become popular for their remarkable capabilities in human-oriented tasks and traditional natural language processing tasks. Its efficient functioning is attributed to the attention mechanism in the Transformer architecture, enabling it to concentrate on particular aspects of the input. LLMs are increasingly being used in domains such as generating prose, poetry or art, which require the model to be creative (e.g. Adobe firefly). LLMs possess advanced language generation abilities that enable them to generate distinctive and captivating content. This utilization of LLMs in generating narratives shows their flexibility and potential for use in domains that extend beyond conventional natural language processing duties. In different contexts, we may expect the LLM to generate factually correct answers, that match reality; e.g., question-answering systems or online assistants. In such situations, being correct is critical to LLMs being trusted in practice. The Bing Chatbot provides its users with the flexibility to select one of the three output modes: creative, balanced, and precise. Each mode emphasizes creativity and factual accuracy differently. In this work, we provide a mathematical abstraction to describe creativity and reality based on certain losses. A model trained on these losses balances the trade-off between the creativity and reality of the model.

cs.CL↗
arXiv2023

Sparse Convolution for Approximate Sparse Instance

Computing the convolution $A \star B$ of two vectors of dimension $n$ is one of the most important computational primitives in many fields. For the non-negative convolution scenario, the classical solution is to leverage the Fast Fourier Transform whose time complexity is $O(n \log n)$. However, the vectors $A$ and $B$ could be very sparse and we can exploit such property to accelerate the computation to obtain the result. In this paper, we show that when $\|A \star B\|_{\geq c_1} = k$ and $\|A \star B\|_{\leq c_2} = n-k$ holds, we can approximately recover the all index in $\mathrm{supp}_{\geq c_1}(A \star B)$ with point-wise error of $o(1)$ in $O(k \log (n) \log(k)\log(k/δ))$ time. We further show that we can iteratively correct the error and recover all index in $\mathrm{supp}_{\geq c_1}(A \star B)$ correctly in $O(k \log(n) \log^2(k) (\log(1/δ) + \log\log(k)))$ time.

cs.DS↗
arXiv2023

Faster Robust Tensor Power Method for Arbitrary Order

Tensor decomposition is a fundamental method used in various areas to deal with high-dimensional data. \emph{Tensor power method} (TPM) is one of the widely-used techniques in the decomposition of tensors. This paper presents a novel tensor power method for decomposing arbitrary order tensors, which overcomes limitations of existing approaches that are often restricted to lower-order (less than $3$) tensors or require strong assumptions about the underlying data structure. We apply sketching method, and we are able to achieve the running time of $\widetilde{O}(n^{p-1})$, on the power $p$ and dimension $n$ tensor. We provide a detailed analysis for any $p$-th order tensor, which is never given in previous works.

cs.LG↗
arXiv2023

Federated Empirical Risk Minimization via Second-Order Method

Many convex optimization problems with important applications in machine learning are formulated as empirical risk minimization (ERM). There are several examples: linear and logistic regression, LASSO, kernel regression, quantile regression, $p$-norm regression, support vector machines (SVM), and mean-field variational inference. To improve data privacy, federated learning is proposed in machine learning as a framework for training deep learning models on the network edge without sharing data between participating nodes. In this work, we present an interior point method (IPM) to solve a general ERM problem under the federated learning setting. We show that the communication complexity of each iteration of our IPM is $\tilde{O}(d^{3/2})$, where $d$ is the dimension (i.e., number of features) of the dataset.

cs.LG↗
arXiv2023

Space-Efficient Interior Point Method, with applications to Linear Programming and Maximum Weight Bipartite Matching

We study the problem of solving linear program in the streaming model. Given a constraint matrix $A\in \mathbb{R}^{m\times n}$ and vectors $b\in \mathbb{R}^m, c\in \mathbb{R}^n$, we develop a space-efficient interior point method that optimizes solely on the dual program. To this end, we obtain efficient algorithms for various different problems: * For general linear programs, we can solve them in $\widetilde O(\sqrt n\log(1/ε))$ passes and $\widetilde O(n^2)$ space for an $ε$-approximate solution. To the best of our knowledge, this is the most efficient LP solver in streaming with no polynomial dependence on $m$ for both space and passes. * For bipartite graphs, we can solve the minimum vertex cover and maximum weight matching problem in $\widetilde O(\sqrt{m})$ passes and $\widetilde O(n)$ space. In addition to our space-efficient IPM, we also give algorithms for solving SDD systems and isolation lemma in $\widetilde O(n)$ spaces, which are the cornerstones for our graph results.

cs.DS↗
arXiv2023

Solving Regularized Exp, Cosh and Sinh Regression Problems

In modern machine learning, attention computation is a fundamental task for training large language models such as Transformer, GPT-4 and ChatGPT. In this work, we study exponential regression problem which is inspired by the softmax/exp unit in the attention mechanism in large language models. The standard exponential regression is non-convex. We study the regularization version of exponential regression problem which is a convex problem. We use approximate newton method to solve in input sparsity time. Formally, in this problem, one is given matrix $A \in \mathbb{R}^{n \times d}$, $b \in \mathbb{R}^n$, $w \in \mathbb{R}^n$ and any of functions $\exp, \cosh$ and $\sinh$ denoted as $f$. The goal is to find the optimal $x$ that minimize $ 0.5 \| f(Ax) - b \|_2^2 + 0.5 \| \mathrm{diag}(w) A x \|_2^2$. The straightforward method is to use the naive Newton's method. Let $\mathrm{nnz}(A)$ denote the number of non-zeros entries in matrix $A$. Let $ω$ denote the exponent of matrix multiplication. Currently, $ω\approx 2.373$. Let $ε$ denote the accuracy error. In this paper, we make use of the input sparsity and purpose an algorithm that use $\log ( \|x_0 - x^*\|_2 / ε)$ iterations and $\widetilde{O}(\mathrm{nnz}(A) + d^ω )$ per iteration time to solve the problem.

cs.LG↗
arXiv2023

Fast Attention Requires Bounded Entries

In modern machine learning, inner product attention computation is a fundamental task for training large language models such as Transformer, GPT-1, BERT, GPT-2, GPT-3 and ChatGPT. Formally, in this problem, one is given as input three matrices $Q, K, V \in [-B,B]^{n \times d}$, and the goal is to construct the matrix $\mathrm{Att}(Q,K,V) := \mathrm{diag}(A {\bf 1}_n)^{-1} A V \in \mathbb{R}^{n \times d}$, where $A = \exp(QK^\top/d)$ is the `attention matrix', and $\exp$ is applied entry-wise. Straightforward methods for this problem explicitly compute the $n \times n$ attention matrix $A$, and hence require time $Ω(n^2)$ even when $d = n^{o(1)}$ is small. In this paper, we investigate whether faster algorithms are possible by implicitly making use of the matrix $A$. We present two results, showing that there is a sharp transition at $B = Θ(\sqrt{\log n})$. $\bullet$ If $d = O(\log n)$ and $B = o(\sqrt{\log n})$, there is an $n^{1+o(1)}$ time algorithm to approximate $\mathrm{Att}(Q,K,V)$ up to $1/\mathrm{poly}(n)$ additive error. $\bullet$ If $d = O(\log n)$ and $B = Θ(\sqrt{\log n})$, assuming the Strong Exponential Time Hypothesis from fine-grained complexity theory, it is impossible to approximate $\mathrm{Att}(Q,K,V)$ up to $1/\mathrm{poly}(n)$ additive error in truly subquadratic time $n^{2 - Ω(1)}$. This gives a theoretical explanation for the phenomenon observed in practice that attention computation is much more efficient when the input matrices have smaller entries.

cs.LG↗
arXiv2023

Attention Scheme Inspired Softmax Regression

Large language models (LLMs) have made transformed changes for human society. One of the key computation in LLMs is the softmax unit. This operation is important in LLMs because it allows the model to generate a distribution over possible next words or phrases, given a sequence of input words. This distribution is then used to select the most likely next word or phrase, based on the probabilities assigned by the model. The softmax unit plays a crucial role in training LLMs, as it allows the model to learn from the data by adjusting the weights and biases of the neural network. In the area of convex optimization such as using central path method to solve linear programming. The softmax function has been used a crucial tool for controlling the progress and stability of potential function [Cohen, Lee and Song STOC 2019, Brand SODA 2020]. In this work, inspired the softmax unit, we define a softmax regression problem. Formally speaking, given a matrix $A \in \mathbb{R}^{n \times d}$ and a vector $b \in \mathbb{R}^n$, the goal is to use greedy type algorithm to solve \begin{align*} \min_{x} \| \langle \exp(Ax), {\bf 1}_n \rangle^{-1} \exp(Ax) - b \|_2^2. \end{align*} In certain sense, our provable convergence result provides theoretical support for why we can use greedy algorithm to train softmax function in practice.

cs.LG↗
arXiv2023

The Closeness of In-Context Learning and Weight Shifting for Softmax Regression

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks. The attention mechanism in the Transformer architecture is a critical component of LLMs, as it allows the model to selectively focus on specific input parts. The softmax unit, which is a key part of the attention mechanism, normalizes the attention scores. Hence, the performance of LLMs in various NLP tasks depends significantly on the crucial role played by the attention mechanism with the softmax unit. In-context learning, as one of the celebrated abilities of recent LLMs, is an important concept in querying LLMs such as ChatGPT. Without further parameter updates, Transformers can learn to predict based on few in-context examples. However, the reason why Transformers becomes in-context learners is not well understood. Recently, several works [ASA+22,GTLV22,ONR+22] have studied the in-context learning from a mathematical perspective based on a linear regression formulation $\min_x\| Ax - b \|_2$, which show Transformers' capability of learning linear functions in context. In this work, we study the in-context learning based on a softmax regression formulation $\min_{x} \| \langle \exp(Ax), {\bf 1}_n \rangle^{-1} \exp(Ax) - b \|_2$ of Transformer's attention mechanism. We show the upper bounds of the data transformations induced by a single self-attention layer and by gradient-descent on a $\ell_2$ regression loss for softmax prediction function, which imply that when training self-attention-only Transformers for fundamental regression tasks, the models learned by gradient-descent and Transformers show great similarity.

cs.CL↗
arXiv2023

PVP: Pre-trained Visual Parameter-Efficient Tuning

Large-scale pre-trained transformers have demonstrated remarkable success in various computer vision tasks. However, it is still highly challenging to fully fine-tune these models for downstream tasks due to their high computational and storage costs. Recently, Parameter-Efficient Tuning (PETuning) techniques, e.g., Visual Prompt Tuning (VPT) and Low-Rank Adaptation (LoRA), have significantly reduced the computation and storage cost by inserting lightweight prompt modules into the pre-trained models and tuning these prompt modules with a small number of trainable parameters, while keeping the transformer backbone frozen. Although only a few parameters need to be adjusted, most PETuning methods still require a significant amount of downstream task training data to achieve good results. The performance is inadequate on low-data regimes, especially when there are only one or two examples per class. To this end, we first empirically identify the poor performance is mainly due to the inappropriate way of initializing prompt modules, which has also been verified in the pre-trained language models. Next, we propose a Pre-trained Visual Parameter-efficient (PVP) Tuning framework, which pre-trains the parameter-efficient tuning modules first and then leverages the pre-trained modules along with the pre-trained transformer backbone to perform parameter-efficient tuning on downstream tasks. Experiment results on five Fine-Grained Visual Classification (FGVC) and VTAB-1k datasets demonstrate that our proposed method significantly outperforms state-of-the-art PETuning methods.

cs.CV↗